Query-document Matching Research Articles

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

Cross-Lingual Information Retrieval (CLIR) aims to rank the documents written in a language different from the user’s query. The intrinsic gap between different languages is an essential challenge for CLIR. In this paper, we introduce the multilingual knowledge graph (KG) to the CLIR task due to the sufficient information of entities in multiple languages. It is regarded as a “silver bullet” to simultaneously perform explicit alignment between queries and documents and also broaden the representations of queries. And we propose a model named CLIR with HIerarchical Knowledge Enhancement (HIKE) for our task. The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism. Particularly, HIKE first integrates the entities and their neighborhood in KG into query representations with a knowledge-level fusion, then combines the knowledge from both source and target languages to further mitigate the linguistic gap with a language-level fusion. Finally, experimental results demonstrate that HIKE achieves substantial improvements over state-of-the-art competitors.

Improving cross-lingual text matching with dual-level collaborative coarse-to-fine filter alignment network

Semantic alignment is a key component in Cross-Language Text Matching (CLTM) to facilitate matching (e.g., query-document matching) between two languages. The current solutions for semantic alignment mainly perform word-level translation directly, without considering the contextual information for the whole query and documents. To this end, we propose a Dual-Level Collaborative Rough-to-Fine Filter Alignment Network (DLCCFA) to achieve better cross-language semantic alignment and document matching. DLCCFA is devised with both a coarse-grained filter in word-level and a fine-grained filter in sentence-level. Concretely, for the query in word-level, we firstly extract top-k translation candidates for each token in the query through a probabilistic bilingual lexicon. Then, a Translation Probability Attention (TPA) mechanism is proposed to obtain coarse-grained word alignment, which generates the corresponding query auxiliary sentence. Afterwards, we further propose a Bilingual Cross Attention and utilize Self-Attention to achieve fine-grained sentence-level filtering, resulting in the cross-language representation of the query. The idea is that each token in the query works as an anchor to filter the semantic noise in the query auxiliary sentence and accurately align semantics of different languages. Extensive experiments on four real-world datasets of six languages demostrate that our method can outperform the mainstream alternatives of CLTM.

Multi-Layer Contextual Passage Term Embedding for Ad-Hoc Retrieval

Nowadays, pre-trained language models such as Bidirectional Encoder Representations from Transformer (BERT) are becoming a basic building block in Information Retrieval tasks. Nevertheless, there are several limitations when applying BERT to the query-document matching task: (1) relevance assessments are applicable at the document-level, and the tokens of documents often exceed the maximum input length of BERT; (2) applying BERT to long documents leads to a great consumption of memory usage and run time, owing to the computational cost of the interactions between tokens. This paper explores a novel multi-layer contextual passage architecture that leverage text summarization extraction to generate passage-level evidence for the pre-selected document passage thus brought new possibilities for the long document relevance task. Experiments were conducted on two standard ad-hoc retrieval collections from the Text Retrieval Conference (TREC) 2004 Robust Track (Robust04) and ClueWeb09 with two different characteristics individually. Experimental results show that our approach can significantly outperform the strong baselines and even compared with the same BERT-based models, the precision of our methods as well as state-of-the-art neural ranking models.

Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization.

Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to the patient. Other factors such as demographic attributes, comorbidities, and social determinants may also be pertinent. As such, the retrieval problem is often formulated as ad hoc search but with multiple facets (e.g., disease, mutation) that may need to be incorporated. In this paper, we present a document reranking approach that combines neural query-document matching and text summarization toward such retrieval scenarios. Our architecture builds on the basic BERT model with three specific components for reranking: (a). document-query matching (b). keyword extraction and (c). facet-conditioned abstractive summarization. The outcomes of (b) and (c) are used to essentially transform a candidate document into a concise summary that can be compared with the query at hand to compute a relevance score. Component (a) directly generates a matching score of a candidate document for a query. The full architecture benefits from the complementary potential of document-query matching and the novel document transformation approach based on summarization along PM facets. Evaluations using NIST's TREC-PM track datasets (2017-2019) show that our model achieves state-of-the-art performance. To foster reproducibility, our code is made available here: https://github.com/bionlproc/text-summ-for-doc-retrieval.

Incremental cluster-based retrieval using compressed cluster-skipping inverted files

We propose a unique cluster-based retrieval (CBR) strategy using a new cluster-skipping inverted file for improving query processing efficiency. The new inverted file incorporates cluster membership and centroid information along with the usual document information into a single structure. In our incremental-CBR strategy, during query evaluation, both best(-matching) clusters and the best(-matching) documents of such clusters are computed together with a single posting-list access per query term. As we switch from term to term, the best clusters are recomputed and can dynamically change. During query-document matching, only relevant portions of the posting lists corresponding to the best clusters are considered and the rest are skipped. The proposed approach is essentially tailored for environments where inverted files are compressed, and provides substantial efficiency improvement while yielding comparable, or sometimes better, effectiveness figures. Our experiments with various collections show that the incremental-CBR strategy using a compressed cluster-skipping inverted file significantly improves CPU time efficiency, regardless of query length. The new compressed inverted file imposes an acceptable storage overhead in comparison to a typical inverted file. We also show that our approach scales well with the collection size.

A system for the retrieval of Italian broadcast news

This paper presents a prototype for the retrieval of Italian broadcast news, which has been developed at ITC-irst. The architecture employs a speech recognition engine for the automatic transcription of audio news. Moreover, it features document indexing based on part-of-speech tagging of text coupled with morphological analysis, and query expansion exploiting the Italian WordNet thesaurus. Query-document matching is based on a statistical term weighting scheme. The system was tested on a 203-story collection of audio news, augmented with 9500 newspaper articles. The evaluation was based on a “known item” retrieval task and aimed at evaluating the impact of speech recognition errors and query expansion on retrieval performance.