English
Related papers

Related papers: Explicit Pairwise Word Interaction Modeling Improv…

200 papers

Sentence fusion is the task of joining related sentences into coherent text. Current training and evaluation schemes for this task are based on single reference ground-truths and do not account for valid fusion variants. We show that this…

Computation and Language · Computer Science 2020-10-07 Eyal Ben-David , Orgad Keller , Eric Malmi , Idan Szpektor , Roi Reichart

Existing work on probing of pretrained language models (LMs) has predominantly focused on sentence-level syntactic tasks. In this paper, we introduce document-level discourse probing to evaluate the ability of pretrained LMs to capture…

Computation and Language · Computer Science 2021-04-14 Fajri Koto , Jey Han Lau , Timothy Baldwin

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

Computation and Language · Computer Science 2019-09-11 Lyan Verwimp , Jerome R. Bellegarda

Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether multilingual sentence…

Computation and Language · Computer Science 2023-01-31 Weikang Wang , Guanhua Chen , Hanqing Wang , Yue Han , Yun Chen

Recently, the bidirectional encoder representations from transformers (BERT) model has attracted much attention in the field of natural language processing, owing to its high performance in language understanding-related tasks. The BERT…

Machine Learning · Computer Science 2020-04-16 Kazuki Miyazawa , Tatsuya Aoki , Takato Horii , Takayuki Nagai

Large language models have made significant advancements in various natural language processing tasks, including coreference resolution. However, traditional methods often fall short in effectively distinguishing referential relationships…

Computation and Language · Computer Science 2025-04-09 Xingzu Liu , Songhang deng , Mingbang Wang , Zhang Dong , Le Dai , Jiyuan Li , Ruilin Nong

Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply…

Computation and Language · Computer Science 2025-12-09 Rajeev Ranjan

Recent work indicated that pretrained language models (PLMs) such as BERT and RoBERTa can be transformed into effective sentence and word encoders even via simple self-supervised techniques. Inspired by this line of work, in this paper we…

Computation and Language · Computer Science 2021-09-21 Qianchu Liu , Fangyu Liu , Nigel Collier , Anna Korhonen , Ivan Vulić

Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for…

Computation and Language · Computer Science 2022-03-15 Yiming Cui , Ziqing Yang , Ting Liu

Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $…

Computation and Language · Computer Science 2020-12-14 Wentao Ma , Yiming Cui , Ting Liu , Dong Wang , Shijin Wang , Guoping Hu

Pre-trained models are widely used in the tasks of natural language processing nowadays. However, in the specific field of text simplification, the research on improving pre-trained models is still blank. In this work, we propose a…

Computation and Language · Computer Science 2022-04-19 Renliang Sun , Xiaojun Wan

Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching. Meanwhile, dependency prior knowledge has also shown general benefits in multiple NLP tasks. However, how to efficiently integrate…

Computation and Language · Computer Science 2023-08-25 Jian Song , Di Liang , Rumei Li , Yuntao Li , Sirui Wang , Minlong Peng , Wei Wu , Yongxin Yu

In recent years BERT shows apparent advantages and great potential in natural language processing tasks. However, both training and applying BERT requires intensive time and resources for computing contextual language representations, which…

Computation and Language · Computer Science 2021-11-05 Tan Huang

Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…

Computation and Language · Computer Science 2021-04-08 Hassan S. Shavarani , Anoop Sarkar

We advance a novel explanation of similarity-based interference effects in subject-verb and reflexive pronoun agreement processing, grounded in surprisal values computed from a pretrained large-scale Transformer model, GPT-2. Specifically,…

Computation and Language · Computer Science 2021-04-28 Soo Hyun Ryu , Richard L. Lewis

The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. A recent significant improvement in these tasks comes…

Computation and Language · Computer Science 2021-06-18 Weidi Xu , Xingyi Cheng , Kunlong Chen , Wei Wang , Bin Bi , Ming Yan , Chen Wu , Luo Si , Wei Chu , Taifeng Wang

Pair-based metric learning has been widely adopted to learn sentence embedding in many NLP tasks such as semantic text similarity due to its efficiency in computation. Most existing works employed a sequence encoder model and utilized…

Computation and Language · Computer Science 2020-05-26 Li Zhang , Han Wang , Lingxiao Li

Recently, there is rising interest in modelling the interactions of two sentences with deep neural networks. However, most of the existing methods encode two sequences with separate encoders, in which a sentence is encoded with little or no…

Computation and Language · Computer Science 2016-05-23 Pengfei Liu , Xipeng Qiu , Xuanjing Huang

There is growing evidence that pretrained language models improve task-specific fine-tuning not just for the languages seen in pretraining, but also for new languages and even non-linguistic data. What is the nature of this surprising…

Computation and Language · Computer Science 2021-04-20 Zhengxuan Wu , Nelson F. Liu , Christopher Potts

Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results [Gupta et al 2018]. In this paper, we present three different improvements to the model: contextualized…

Computation and Language · Computer Science 2019-02-19 Arash Einolghozati , Panupong Pasupat , Sonal Gupta , Rushin Shah , Mrinal Mohit , Mike Lewis , Luke Zettlemoyer