Multi-turn Response Selection Research Articles

Improving BERT with local context comprehension for multi-turn response selection in retrieval-based dialogue systems

Multi-turn response selection is an important branch in the field of natural language processing, which aims to select the most appropriate response based on multi-turn dialogue. Most state-of-the-art models adopt pre-trained language models (PrLMs) and multiple auxiliary tasks to enhance their ability to understand the semantics in multi-turn dialogue. However, some critical challenges still remain to be addressed. Optimizing multiple auxiliary tasks simultaneously may significantly increase the training cost. Meanwhile, the semantic gap between the optimization objectives of the main and auxiliary tasks may bring noise to pre-trained language models. To address these challenges, we propose an efficient BERT-based neural network model with local context comprehension (BERT-LCC) for multi-turn response selection. First, we propose a self-supervised learning strategy, which introduces an auxiliary task named Response Prediction in Random Sliding Windows (RPRSW). In a multi-turn dialogue, the RPRSW task takes utterances falling within a random sliding window as input and predicts whether the last utterance within the sliding window is the appropriate response for the local dialogue context. This auxiliary task can enhance BERT’s understanding of local semantic information. Second, we propose a local information fusion (LIF) mechanism that collects multi-granularity local features at different dialogue stages and employs a gating function to fuse global features with local features. Third, we introduce a simple but effective domain learning strategy to learn rich semantic information at different dialogue stages during pre-training. Experimental results on two public benchmark datasets show that BERT-LCC outperforms other state-of-the-art models.

Learning Multi-turn Response Selection in Grounded Dialogues with Reinforced Knowledge and Context Distillation

Recently, knowledge-grounded dialogue systems have gained increasing attention. Great efforts have been made to build response matching models where all dialogue content and knowledge sentences are leveraged. However, knowledge redundancy and distraction of irrelevant dialogue content often exist in knowledge-grounded conversations, which may affect the matching process and lead to inferior performance. In addition, irrelevant dialogue history and excessive knowledge also hinder the exploitation of popular pre-trained language models (PLMs) due to the limitation of input length. To address these challenges, we propose a new knowledge-grounded dialogue model based on PLMs, where a knowledge selector and a context selector are designed for filtering out irrelevant knowledge sentences and redundant dialogue history, respectively. Considering the lack of labeled data for the learning of two selectors, we pre-train them with weakly-supervised tasks and then jointly conduct the optimization of knowledge and context selection and fine-tuning of PLMs for response ranking with reinforcement learning (RL). By this means, the dialogue model can distill more accurate and concise knowledge and dialogue content for subsequent response ranking module, and the overall model can converge and perform better. We conduct experiments on two benchmarks and evaluation results indicate that our model can significantly outperform the state-of-the-art methods.

SAM: Multi-turn Response Selection Based on Semantic Awareness Matching

Multi-turn response selection is a key issue in retrieval-based chatbots and has attracted considerable attention in the NLP (Natural Language processing) field. So far, researchers have developed many solutions that can select appropriate responses for multi-turn conversations. However, these works are still suffering from the semantic mismatch problem when responses and context share similar words with different meanings. In this article, we propose a novel chatbot model based on Semantic Awareness Matching, called SAM. SAM can capture both similarity and semantic features in the context by a two-layer matching network. Appropriate responses are selected according to the matching probability made through the aggregation of the two feature types. In the evaluation, we pick 4 widely used datasets and compare SAM’s performance to that of 12 other models. Experiment results show that SAM achieves substantial improvements, with up to 1.5% R 10 @1 on Ubuntu Dialogue Corpus V2, 0.5% R 10 @1 on Douban Conversation Corpus, and 1.3% R 10 @1 on E-commerce Corpus.

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language units from multiple granularities (e.g., words, phrases, and sub-sentences, etc.); (2) local (e.g., a small window around a word) and long-range (e.g., words across the context and the response) dependencies may exist in dialogue data; and (3) the relationship between the context and the response candidate lies in multiple relevant semantic clues or relatively implicit semantic clues in some real cases. However, existing approaches usually encode the dialogue with mono-type representation and the interaction processes between the context and the response candidate are executed in a rather shallow manner, which may lead to an inadequate understanding of dialogue content and hinder the recognition of the semantic relevance between the context and response. To tackle these challenges, we propose a representation [ K ] -interaction [ L ] -matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection. Particularly, we construct different types of representations for utterance–response pairs and deepen them via alternate encoding and interaction. By this means, the model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair. Experiment results on three public benchmarks indicate that the proposed model significantly outperforms previous conventional context-response matching models and achieve slightly better results than the BERT model for multi-turn response selection in retrieval-based dialogue systems.

Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is a great challenging task. Existing studies focus on building a context-response matching model with various neural architectures or pretrained language models (PLMs) and typically learning with a single response prediction task. These approaches overlook many potential training signals contained in dialogue data, which might be beneficial for context understanding and produce better features for response prediction. Besides, the response retrieved from existing dialogue systems supervised by the conventional way still faces some critical challenges, including incoherence and inconsistency. To address these issues, in this paper, we propose learning a context-response matching model with auxiliary self-supervised tasks designed for the dialogue data based on pre-trained language models. Specifically, we introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination, and jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. By this means, the auxiliary tasks can guide the learning of the matching model to achieve a better local optimum and select a more proper response. Experiment results on two benchmarks indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection in retrieval-based dialogues, and our model achieves new state-of-the-art results on both datasets.

A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training

We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features, leading to insufficient model reasoning ability. In this paper, we propose a graph- reasoning network (GRN) to address the problem. GRN first conducts pre-training based on ALBERT using next utterance prediction and utterance order prediction tasks specifically devised for response selection. These two customized pre-training tasks can endow our model with the ability of capturing semantical and chronological dependency between utterances. We then fine-tune the model on an integrated network with sequence reasoning and graph reasoning structures. The sequence reasoning module conducts inference based on the highly summarized context vector of utterance-response pairs from the global perspective. The graph reasoning module conducts the reasoning on the utterance-level graph neural network from the local perspective. Experiments on two conversational reasoning datasets show that our model can dramatically outperform the strong baseline methods and can achieve performance which is close to human-level.

Hierarchical matching network for multi-turn response selection in retrieval-based chatbots

Proper response selection is a crucial challenge in retrieval-based chatbots. The state-of-the-art methods match a response with the word sequence of a context, or match the response with each utterance in the context and then accumulate matching information. The former architecture could lose some important local matching information in utterance–response pairs and does not explicitly capture the relationships and dependencies among utterances. The latter architecture does not consider the important global matching information because there is no match between the response and the context at word level. Hence, the above methods have a problem, without considering the fact that matching a response with different levels of a context could match different information for multi-turn response selection. In this work, we propose a hierarchical matching network to match a response with the word and utterance level of a context. At word level, we concatenate the multi-turn context as a long word sequence and then adopt a text matching model to match the response with the word sequence which can capture important matching information at word level. At utterance level, we employ the identical text matching model to match the response with each utterance in the context to capture important matching information for each utterance–response pair and then accumulate the matching information by a recurrent neural network to model the relationships of utterances. At last, the hierarchical matching information is fused to get the final matching information. Experiments on two large-scale public multi-turn response selection datasets show that the proposed model significantly outperforms the state-of-the-art baseline models.

Deep Contextualized Utterance Representations for Response Selection and Dialogue Analysis

The NOESIS II challenge, as the Track 2 in the Eighth Dialogue System Technology Challenge (DSTC 8), is the extension of Track 1 in DSTC 7. Three new elements are incorporated into the extended track, i.e., dialogue with multiple participants, dialogue success, and dialogue disentanglement. These are vital for the creation of a deployed task-oriented dialogue system. This track is divided into four subtasks, the first two of which are evaluated in the form of response selection and the last two focus on dialogue analysis. This paper describes our methods developed for these four subtasks, which all employ deep contextualized utterance representations to make models aware of contextual information and to keep the intrinsic property of multi-turn dialogue systems. In the released evaluation results of Track 2 in DSTC 8, our proposed methods ranked fourth in subtask 1, third in subtask 2, and first in subtask 3 and subtask 4 respectively. In addition to the challenge tasks, we also compare our proposed methods with previous ones on public benchmark datasets. Experimental results show that our proposed methods outperform existing ones by large margins and achieve new state-of-the-art performances on multi-turn response selection and dialogue disentanglement.

Multi-Turn Response Selection in Retrieval Based Chatbots with Hierarchical Residual Matching Network

Response selection in retrieval-based chatbot aims to find the most relevant response in a candidate repository given the conversation context. A key technique to this task lies in how to measure the matching degree between conversation context and response at rich semantic information. In this paper, we propose a hierarchical residual matching network (HRMN) to fully extract and make use of the rich semantic information in the conversation history and response for themulti-turn response selection task. We empirically verify HRMN on two benchmark data sets and compare against advanced approaches. Evaluation results demonstrate that HRMN outperforms strong baselines and has a distinct improvement in response selection.

Deep context modeling for multi-turn response selection in dialogue systems

Multi-turn response selection is a major task in building intelligent dialogue systems. Most existing works focus on modeling the semantic relationship between the utterances and the candidate response with neural networks like RNNs and various attention mechanisms. In this paper, we study how to leverage the advantage of pre-trained language models (PTMs) to multi-turn response selection in retrieval-based chatbots. We propose a deep context modeling architecture (DCM) for multi-turn response selection by utilizing BERT as the context encoder. DCM is formulated as a four-module architecture, namely contextual encoder, utterance-to-response interaction, features aggregation, and response selection. Moreover, in DCM, we introduce the next utterance prediction as a pre-training scheme based on BERT, aiming to adapt general BERT to accommodate the inherent context continuity underlying the multi-turn dialogue. Taking BERT as the backbone encoder, we then investigate a variety of strategies to perform response selection with comprehensive comparisons. Empirical results on three public datasets from two different languages show that our proposed model outperforms existing promising models significantly, pushing recall to 86.8% (+5.2% improvement over BERT) on Ubuntu Dialogue corpus, recall to 68.5% (+6.4% improvement over BERT) on E-Commerce Dialogue corpus, MAP and MRR to 61.6% and 64.9% respectively (+2.3% and 1.8% improvement over BERT) on Douban Conversation corpus, achieving new state-of-the-art performance for multi-turn response selection.

Sequential neural networks for noetic end-to-end response selection

The noetic end-to-end response selection challenge as one track in the 7th Dialog System Technology Challenges (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context. This paper presents our systems that are ranked top 1 on both datasets under this challenge, one focused and small (Advising) and the other more diverse and large (Ubuntu). Previous state-of-the-art models use hierarchy-based (utterance-level and token-level) neural networks to explicitly model the interactions among different turns’ utterances for context modeling. In this paper, we investigate a sequential matching model based only on chain sequence for multi-turn response selection. Our results demonstrate that the potentials of sequential matching approaches have not yet been fully exploited in the past for multi-turn response selection. In addition to ranking top 1 in the challenge, the proposed model outperforms all previous models, including state-of-the-art hierarchy-based models, on two large-scale public multi-turn response selection benchmark datasets.

Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

This article proposes an utterance-to-utterance interactive matching network (U2U-IMN) for multi-turn response selection in retrieval-based chatbots. Different from previous methods following context-to-response matching or utterance-to-response matching frameworks, this model treats both contexts and responses as sequences of utterances when calculating the matching degrees between them. For a context-response pair, the U2U-IMN model first encodes each utterance separately using recurrent and self-attention layers. Then, a global and bidirectional interaction between the context and the response is conducted using the attention mechanism to collect the matching information between them. The distances between context and response utterances are employed as a prior component when calculating the attention weights. Finally, sentence-level aggregation and context-response-level aggregation are executed in turn to obtain the feature vector for matching degree prediction. Experiments on four public datasets showed that our proposed method outperformed baseline methods on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.

Learning bi-utterance for multi-turn response selection in retrieval-based chatbots

Multi-turn response selection is essential to retrieval-based chatbots. The task requires multi-turn response selection model to match a response candidate with a conversation context. Existing methods may lose relationship features in the context. In this article, we propose an improved method that extends the learning granularity of the multi-turn response selection model to enhance the model’s ability to learn relationship features of utterances in the context, which is a key to understand a conversation context for multi-turn response selection in retrieval-based chatbots. The experimental results show that our proposed method significantly improves sequential matching network for multi-turn response selection in retrieval-based chatbots.

A Sequential Matching Framework for Multi-Turn Response Selection in Retrieval-Based Chatbots

We study the problem of response selection for multi-turn conversation in retrieval-based chatbots. The task involves matching a response candidate with a conversation context, the challenges for which include how to recognize important parts of the context, and how to model the relationships among utterances in the context. Existing matching methods may lose important information in contexts as we can interpret them with a unified framework in which contexts are transformed to fixed-length vectors without any interaction with responses before matching. This motivates us to propose a new matching framework that can sufficiently carry important information in contexts to matching and model relationships among utterances at the same time. The new framework, which we call a sequential matching framework (SMF), lets each utterance in a context interact with a response candidate at the first step and transforms the pair to a matching vector. The matching vectors are then accumulated following the order of the utterances in the context with a recurrent neural network (RNN) that models relationships among utterances. Context-response matching is then calculated with the hidden states of the RNN. Under SMF, we propose a sequential convolutional network and sequential attention network and conduct experiments on two public data sets to test their performance. Experiment results show that both models can significantly outperform state-of-the-art matching methods. We also show that the models are interpretable with visualizations that provide us insights on how they capture and leverage important information in contexts for matching.

Multi-Turn Response Selection for Chatbots With Hierarchical Aggregation Network of Multi-Representation

Matching an appropriate response with its multi-turn context is a crucial challenge in retrieval-based chatbots. Current studies construct multiple representations of context and response to facilitate response selection, but they use these representations in isolation and ignore the relationships among representations. To address these problems, we propose a hierarchical aggregation network of multi-representation (HAMR) to leverage abundant representations sufficiently and enhance valuable information. First, we employ bidirectional recurrent neural networks (BiRNN) to extract syntactic and semantic representations of sentences and use a self-aggregation mechanism to combine these representations. Second, we design a matching aggregation mechanism for fusing different matching information between each utterance in context and response, which is generated by an attention mechanism. By considering the candidate response as the real part of the context, we try to integrate all of them in chronological order and then accumulate the vectors to calculate the final matching degree. An extensive empirical study on two multi-turn response selection data sets indicates that our proposed model achieves a new state-of-the-art result.