no code implementations • ACL (EvalNLGEval, INLG) 2020 • Stephanie Schoch, Diyi Yang, Yangfeng Ji
Despite recent efforts reviewing current human evaluation practices for natural language generation (NLG) research, the lack of reported question wording and potential for framing effects or cognitive biases influencing results has been widely overlooked.
no code implementations • 24 May 2022 • Aidan San, Jan Bakus, Colin Lockard, David Ciemiewicz, Yangfeng Ji, Sandeep Atluri, Kevin Small, Heba Elfardy
In this work, we introduce the PLAtE (Pages of Lists Attribute Extraction) dataset as a challenging new web extraction task.
no code implementations • 19 May 2022 • Wanyu Du, Hanjie Chen, Yangfeng Ji
The natural language generation (NLG) module in task-oriented dialogue systems translates structured meaning representations (MRs) into text responses, which has a great impact on users' experience as the human-machine interaction interface.
no code implementations • 10 May 2022 • Arshdeep Sekhon, Yangfeng Ji, Matthew B. Dwyer, Yanjun Qi
Recent literature has seen growing interest in using black-box strategies like CheckList for testing the behavior of NLP models.
no code implementations • insights (ACL) 2022 • Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah, Yangfeng Ji
Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from.
1 code implementation • 4 Apr 2022 • Wanyu Du, Jianqiao Zhao, LiWei Wang, Yangfeng Ji
The proposed stochastic function is sampled from a Gaussian process prior to (1) provide infinite number of joint Gaussian distributions of random context variables (diversity-promoting) and (2) explicitly model dependency between context variables (accurate-encoding).
1 code implementation • 23 Mar 2022 • Hanjie Chen, Yangfeng Ji
Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms.
no code implementations • 14 Feb 2022 • Jianqiao Zhao, Yanyang Li, Wanyu Du, Yangfeng Ji, Dong Yu, Michael R. Lyu, LiWei Wang
Hence, we propose segment act, an extension of dialog act from utterance level to segment level, and crowdsource a large-scale dataset for it.
no code implementations • 11 Jan 2022 • Hanjie Chen, Yangfeng Ji
We adapt two perturbation-based post-hoc interpretation methods, Leave-one-out and Sampling Shapley, to identify words in inputs that cause the uncertainty in predictions.
no code implementations • 15 Dec 2021 • Andrew Wang, Mohit Sudhakar, Yangfeng Ji
We hypothesize the existence of a low-dimensional toxic subspace in the latent space of pre-trained language models, the existence of which suggests that toxic features follow some underlying pattern and are thus removable.
1 code implementation • Findings (EMNLP) 2021 • Wanyu Du, Yangfeng Ji
Transformer-based pre-trained language models boost the performance of open-domain dialogue systems.
no code implementations • INLG (ACL) 2021 • Stephanie Schoch, Wanyu Du, Yangfeng Ji
Text style transfer involves rewriting the content of a source sentence in a target style.
1 code implementation • EMNLP (BlackboxNLP) 2021 • Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi
Via a small portion of word-level swaps, these adversarial perturbations aim to make the resulting text semantically and spatially similar to its seed input (therefore sharing similar interpretations).
1 code implementation • NAACL 2021 • Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji
Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features.
no code implementations • ACL (GEM) 2021 • Sebastian Gehrmann, Tosin Adewumi, Karmanya Aggarwal, Pawan Sasanka Ammanamanchi, Aremu Anuoluwapo, Antoine Bosselut, Khyathi Raghavi Chandu, Miruna Clinciu, Dipanjan Das, Kaustubh D. Dhole, Wanyu Du, Esin Durmus, Ondřej Dušek, Chris Emezue, Varun Gangal, Cristina Garbacea, Tatsunori Hashimoto, Yufang Hou, Yacine Jernite, Harsh Jhamtani, Yangfeng Ji, Shailza Jolly, Mihir Kale, Dhruv Kumar, Faisal Ladhak, Aman Madaan, Mounica Maddela, Khyati Mahajan, Saad Mahamood, Bodhisattwa Prasad Majumder, Pedro Henrique Martins, Angelina McMillan-Major, Simon Mille, Emiel van Miltenburg, Moin Nadeem, Shashi Narayan, Vitaly Nikolaev, Rubungo Andre Niyongabo, Salomey Osei, Ankur Parikh, Laura Perez-Beltrachini, Niranjan Ramesh Rao, Vikas Raunak, Juan Diego Rodriguez, Sashank Santhanam, João Sedoc, Thibault Sellam, Samira Shaikh, Anastasia Shimorina, Marco Antonio Sobrevilla Cabezudo, Hendrik Strobelt, Nishant Subramani, Wei Xu, Diyi Yang, Akhila Yerukola, Jiawei Zhou
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics.
Ranked #1 on
Data-to-Text Generation
on WebNLG ru
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+5
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Hannah Chen, Yangfeng Ji, David Evans
Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size.
no code implementations • EMNLP 2020 • Yangfeng Ji, Antoine Bosselut, Thomas Wolf, Asli Celikyilmaz
Neural Language Generation (NLG) {--} using neural network models to generate coherent text {--} is among the most promising methods for automated text creation.
2 code implementations • EMNLP 2020 • Hanjie Chen, Yangfeng Ji
To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations.
1 code implementation • COLING 2020 • Sanxing Chen, Aidan San, Xiaodong Liu, Yangfeng Ji
In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and the SQL query to the structured knowledge in the database.
1 code implementation • EMNLP 2021 • Sanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao, Ruofei Zhang, Yangfeng Ji
Our proposed model consists of two different Transformer blocks: the bottom block extracts features of each entity-relation pair in the local neighborhood of the source entity and the top block aggregates the relational information from outputs of the bottom block.
no code implementations • ACL 2020 • Hannah Chen, Yangfeng Ji, David Evans
The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either paraphrases or non-paraphrases.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • John X. Morris, Eli Lifland, Jack Lanchantin, Yangfeng Ji, Yanjun Qi
State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack.
2 code implementations • ACL 2020 • Hanjie Chen, Guangtao Zheng, Yangfeng Ji
Experiments show the effectiveness of the proposed method in providing explanations that are both faithful to models and interpretable to humans.
no code implementations • 10 Sep 2019 • Hanjie Chen, Yangfeng Ji
Experiments show the proposed data augmentation methods significantly improve the explainability of both neural classifiers.
1 code implementation • IJCNLP 2019 • Wanyu Du, Yangfeng Ji
Generating paraphrases from given sentences involves decoding words step by step from a large vocabulary.
no code implementations • NAACL 2018 • Elizabeth Clark, Yangfeng Ji, Noah A. Smith
We introduce an approach to neural text generation that explicitly represents entities mentioned in the text.
2 code implementations • EMNLP 2017 • Yangfeng Ji, Chenhao Tan, Sebastian Martschat, Yejin Choi, Noah A. Smith
Understanding a long document requires tracking how entities are introduced and evolve over time.
1 code implementation • ACL 2017 • Yangfeng Ji, Noah Smith
We show that discourse structure, as defined by Rhetorical Structure Theory and provided by an existing discourse parser, benefits text categorization.
4 code implementations • 15 Jan 2017 • Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin
In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.
1 code implementation • 31 Mar 2016 • Yi Luan, Yangfeng Ji, Mari Ostendorf
In this paper, we present a conversational model that incorporates both context and participant role for two-party conversations.
1 code implementation • 7 Mar 2016 • Yangfeng Ji, Gholamreza Haffari, Jacob Eisenstein
This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences.
1 code implementation • 12 Nov 2015 • Yangfeng Ji, Trevor Cohn, Lingpeng Kong, Chris Dyer, Jacob Eisenstein
Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure.
no code implementations • EMNLP 2015 • Parminder Bhatia, Yangfeng Ji, Jacob Eisenstein
Discourse structure is the hidden link between surface features and document-level properties, such as sentiment polarity.
no code implementations • IJCNLP 2015 • Michel Galley, Chris Brockett, Alessandro Sordoni, Yangfeng Ji, Michael Auli, Chris Quirk, Margaret Mitchell, Jianfeng Gao, Bill Dolan
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs.
no code implementations • HLT 2015 • Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, Bill Dolan
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations.
no code implementations • TACL 2015 • Yangfeng Ji, Jacob Eisenstein
A more subtle challenge is that it is not enough to represent the meaning of each argument of a discourse relation, because the relation may depend on links between lowerlevel components, such as entity mentions.
no code implementations • 17 Dec 2014 • Yangfeng Ji, Jacob Eisenstein
A more subtle challenge is that it is not enough to represent the meaning of each sentence of a discourse relation, because the relation may depend on links between lower-level elements, such as entity mentions.
no code implementations • 25 Nov 2014 • Yangfeng Ji, Jacob Eisenstein
Discourse relations bind smaller linguistic units into coherent texts.
1 code implementation • TACL 2014 • Wei Xu, Alan Ritter, Chris Callison-Burch, William B. Dolan, Yangfeng Ji
We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter.