Papers with matching
One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues (P19-1)
Copied to clipboard
| Challenge: | Currently, retrieval-based dialogues are performed in shallow ways . a recent study investigated the problem of context-response matching in open-domain . |
| Approach: | They propose a model that lets utterance-response interaction go deep by stacking interaction blocks. |
| Outcome: | The proposed model outperforms state-of-the-art methods on three benchmark data sets. |
Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension (D19-58)
Copied to clipboard
| Challenge: | Experimental results show that unified model outperforms other models that treat encoding and matching separately. |
| Approach: | They evaluate a unified model with Transformer layers for machine reading comprehension . they find that the model learns different modeling strategies compared with previous models . |
| Outcome: | The unified model outperforms models with Transformer layers on the machine reading comprehension task. |
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)
Copied to clipboard
| Challenge: | Entity matching (EM) is a critical step in entity resolution (ER). |
| Approach: | They propose a method that incorporates record interactions from different perspectives. |
| Outcome: | The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness. |
The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) can explain quantum mechanics and write sophisticated code, yet fail to parse sentences like "The cat that the mouse feared chased meowed" |
| Approach: | They propose a framework to distinguish structural understanding from semantic pattern matching . they use a set of 9,720 comprehension questions on center-embedded sentences . |
| Outcome: | a new framework shows that models lose performance when they abandon structural analysis for semantic associations. |
LATEX-Numeric: Language Agnostic Text Attribute Extraction for Numeric Attributes (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing methods for training numeric attributes are based on manual labeling and distant supervision leads to incomplete training annotations. |
| Approach: | They propose a multi-task learning architecture to deal with missing attribute values in training data, removing dependency on manual annotations. |
| Outcome: | The proposed framework improves on 20 numeric attributes extracted from 5 product categories and 3 english marketplaces with language-agnostic performance. |
Valet: Rule-Based Information Extraction for Rapid Deployment (2022.lrec-1)
Copied to clipboard
| Challenge: | a number of machine learning models can be trained to perform sentence-level information extraction at accuracies ranging from strong to adequate. |
| Approach: | They propose a Python framework for rule-based information extraction that allows for complex matching. |
| Outcome: | The proposed framework can be used to perform rule-based information extraction on examples. |
Pretraining and Finetuning Language Models on Geospatial Networks for Accurate Address Matching (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to address matching and building authoritative address catalogues are limited in data quality and require labeling effort to develop accurate models. |
| Approach: | They propose to view addresses as an address graph and curate inputs by placing geospatially linked addresses in the same context. |
| Outcome: | The proposed framework improves address matching and fine-tuning language models. |
Aspect-based Key Point Analysis for Quantitative Summarization of Reviews (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on review summarization use only major opinions, but ignore minority opinions and fail to quantify opinion prevalence. |
| Approach: | They propose a framework for quantitative review summarization using aspect-based key point analysis (ABKPA) they use aspect-basic sentiment analysis to automatically annotate silver labels for matching aspect-sentiment pairs . |
| Outcome: | The proposed framework outperforms state-of-the-art baselines on Yelp reviews on five business categories. |
A BERT-based Dual Embedding Model for Chinese Idiom Prediction (2020.coling-main)
Copied to clipboard
| Challenge: | Chinese idioms are special fixed phrases whose meanings are often highly idiomatic and non-compositional. |
| Approach: | They propose to use a BERT-based dual embedding model to encode contextual words and learn dual embeds of the idioms. |
| Outcome: | The proposed model performs better than the existing state of the art on a Chinese idiom cloze dataset. |
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. |
| Approach: | They propose to use simple neural models and simple embeddings to improve document matching by taking significantly less training time, energy, and memory. |
| Outcome: | The proposed models outperform the more complex BERT-based models while taking significantly less training time, energy, and memory. |
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for document matching are limited by the partial nature of the sentence-level matching signals. |
| Approach: | They propose a matching approach that equips existing document matching models with an Optimal Partial Transport component, namely OPT-Match, which selects the key sentences that play a major role in matching. |
| Outcome: | The proposed approach outperforms existing models on four publicly available datasets and the key sentences selected by it are consistent with human-provided rationales. |
BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Currently, pre-trained language model (PLM) based metrics are widely adopted in text generation tasks. |
| Approach: | They propose to use PLMs to encode stereotypical societal biases in PLM-based metrics . they show that popular metrics exhibit higher social bias than traditional metrics based on 6 attributes . |
| Outcome: | The proposed method shows that PLM-based metrics exhibit higher social bias than traditional metrics on 6 attributes. |
BERT Is Not The Count: Learning to Match Mathematical Statements with Proofs (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing work on mathematical article analysis uses natural language processing to solve complex mathematical articles. |
| Approach: | They propose a bilinear similarity model and two decoding methods to match statements to proofs effectively. |
| Outcome: | The proposed model matches proofs to statements without being aware of proofs, but it follows a relatively shallow symbolic analysis and matching to achieve that performance. |
Original Semantics-Oriented Attention and Deep Fusion Network for Sentence Matching (D19-1)
Copied to clipboard
| Challenge: | Sentence matching is a key issue in natural language inference and paraphrase identification. |
| Approach: | They propose a semantics-oriented attention and deep fusion network (OSOA-DFN) that is oriented to the original semantic representation of another sentence and propagates attention information at each matching layer. |
| Outcome: | The proposed model can model sentence matching more precisely on three sentence matching benchmark datasets. |
EDIS: Entity-Driven Image Search over Multimodal Web Content (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing image retrieval methods require large datasets and a large candidate set. |
| Approach: | They propose a news-domain dataset for cross-modal image search with 1 million web images . they propose combining multimodal image-text pairs with a million candidates . |
| Outcome: | The proposed dataset challenges state-of-the-art methods with dense entities and the large-scale candidate set. |
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models (2025.coling-main)
Copied to clipboard
Haoran Lian, Junmin Chen, Wei Huang, Yizhe Xiong, Wenping Hu, Guiguang Ding, Hui Chen, Jianwei Niu, Zijia Lin, Fuzheng Zhang, Di Zhang
| Challenge: | Recent studies show that Large language models struggle with handling long token sequences due to limited training context size. |
| Approach: | They propose a single-stage continual pretraining method to equip LLMs with long context modeling capabilities. |
| Outcome: | The proposed method outperforms existing methods on 4 language modeling benchmarks. |
CNM: An Interpretable Complex-valued Network for Matching (N19-1)
Copied to clipboard
| Challenge: | Existing work on quantum physics models language understanding using quantum probability . |
| Approach: | They propose a quantum-theoretic framework that unifies different linguistic units in a single complex-valued vector space and a complex-valuable network for semantic matching. |
| Outcome: | The proposed framework achieves comparable performances to strong CNN and RNN baselines on two benchmarking question answering (QA) datasets. |
How to Talk to Language Models: Serialization Strategies for Structured Entity Matching (2025.findings-naacl)
Copied to clipboard
| Challenge: | Entity matching (EM) identifies whether two data records refer to the same entity . however, its performance heavily depends on how structured entities are “talked” through serialized text. |
| Approach: | They propose a novel serialization scheme for entities with complex relations in knowledge graphs based on random walks and use open-source LLMs to encode sampled semantic walks for matching. |
| Outcome: | The proposed scheme achieves leading performance on EM in canonical and heterogeneous KGs. |
Embedding Meta-Textual Information for Improved Learning to Rank (2020.coling-main)
Copied to clipboard
| Challenge: | a neural representation learning approach has not been extended to meta-textual information that is readily available for many IR tasks. |
| Approach: | They propose a framework that learns embeddings for meta-textual categories and optimizes a pairwise ranking objective for improved matching based on combined embedds of textual and meta-tactile information. |
| Outcome: | The proposed framework improves cross-lingual retrieval in the Wikipedia domain and Patent domain. |
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)
Copied to clipboard
Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng
| Challenge: | Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps. |
| Approach: | They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts. |
| Outcome: | The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models. |
Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems. |
| Approach: | They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence. |
| Outcome: | The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets. |
Overcoming the Long Tail Problem: A Case Study on CO2-Footprint Estimation of Recipes using Information Retrieval (L18-1)
Copied to clipboard
| Challenge: | a particular challenge is the "long tail problem" that arises with the large diversity of possible ingredients. |
| Approach: | They propose methods that use information retrieval methods for automatic calculation of CO2-footprints of cooking recipes. |
| Outcome: | The proposed methods are generalizable to other use cases where a numerical value has to be calculated based on a list of textual elements. |
A Semantic Filter Based on Relations for Knowledge Graph Completion (2021.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge graph embedding is a new form of knowledge graphing that allows for better link prediction. |
| Approach: | They propose to use relational embedding to fit symmetry/antisymmetry and combination relationships. |
| Outcome: | The proposed model can fit symmetry/antisymmetry and combination relationships. |
Multi-Granularity Fusion Text Semantic Matching Based on WoBERT (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing text-matching methods struggle with semantic nuances in short texts . a novel approach to improve text semantic matching is being developed . |
| Approach: | They propose a multi-granularity fusion model that harnesses a pre-trained language model to capture text semantic nuances. |
| Outcome: | The proposed model improves on Chinese short text matching datasets compared to traditional methods . the proposed model captures individual text semantic nuances and improves accuracy . |
A Text-Based Recommender System that Leverages Explicit Affective State Preferences (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems that leverage user preferences that are implicit in user-item rating histories can be slow to track changes in user preferences and imprecise for users with diverse preferences. |
| Approach: | They propose a novel recommendation task that leverages a wide range of affective states sought explicitly by the user to identify items that induce those affective state. |
| Outcome: | The proposed model can leverage a wide range of affective states sought explicitly by the user to identify items likely to induce those affective state. |