Yiming Yang


2021

pdf bib
不同类型噪声环境下言语理解的脑机制研究(Brain Mechanism of Speech Comprehension in Different Noise Conditions)
Libo Geng (耿立波) | Zixuan Xue (薛紫炫) | Yiming Yang (杨亦鸣)
Proceedings of the 20th Chinese National Conference on Computational Linguistics

“文章使用ERP技术,对比分析了安静、白噪声、汉语噪声、英语噪声四种听觉条件下,听力正常的汉语母语者加工汉语句子的情况,以探究信息掩蔽条件下语义加工的神经机制。研究发现不同噪声条件下诱发的N100、N400、LPC等ERPs成分具有不同的波形表现,据此本文得出以下结论:首先,在语音掩蔽条件下,对于难度较大的语义加工,目标语音与掩蔽噪声在知觉层面的相似性并非主要影响因素,而掩蔽噪声语义内容上的可懂度发挥着更关键的作用。其次,当言语噪声为听者极其熟悉或完全陌生的语言,其对语义加工的掩蔽干扰较小,而当掩蔽噪声为听者接触过的语言但不是母语或主要语言,其掩蔽效应可能更强。最后,不熟悉的言语噪声中所包含的出现频率较小但能够被听者理解的语义内容,与听者的预期相冲突,引发听者的注意转移,这些语义信息被传输至听觉中枢神经,占用了原本用于目标刺激的认知资源,从而增强了信息掩蔽的效果。”

pdf bib
Neural Language Modeling for Contextualized Temporal Graph Generation
Aman Madaan | Yiming Yang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

This paper presents the first study on using large-scale pre-trained language models for automated generation of an event-level temporal graph for a document. Despite the huge success of neural pre-training methods in NLP tasks, its potential for temporal reasoning over event graphs has not been sufficiently explored. Part of the reason is the difficulty in obtaining large training corpora with human-annotated events and temporal links. We address this challenge by using existing IE/NLP tools to automatically generate a large quantity (89,000) of system-produced document-graph pairs, and propose a novel formulation of the contextualized graph generation problem as a sequence-to-sequence mapping task. These strategies enable us to leverage and fine-tune pre-trained language models on the system-induced training data for the graph generation task. Our experiments show that our approach is highly effective in generating structurally and semantically valid graphs. Further, evaluation on a challenging hand-labeled, out-of-domain corpus shows that our method outperforms the closest existing method by a large margin on several metrics. We also show a downstream application of our approach by adapting it to answer open-ended temporal questions in a reading comprehension setting.

pdf bib
Could you give me a hint ? Generating inference graphs for defeasible reasoning
Aman Madaan | Dheeraj Rajagopal | Niket Tandon | Yiming Yang | Eduard Hovy
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

2020

pdf bib
Politeness Transfer: A Tag and Generate Approach
Aman Madaan | Amrith Setlur | Tanmay Parekh | Barnabas Poczos | Graham Neubig | Yiming Yang | Ruslan Salakhutdinov | Alan W Black | Shrimai Prabhumoye
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning. We also provide a dataset of more than 1.39 instances automatically labeled for politeness to encourage benchmark evaluations on this new task. We design a tag and generate pipeline that identifies stylistic attributes and subsequently generates a sentence in the target style while preserving most of the source content. For politeness as well as five other transfer tasks, our model outperforms the state-of-the-art methods on automatic metrics for content preservation, with a comparable or better performance on style transfer accuracy. Additionally, our model surpasses existing methods on human evaluations for grammaticality, meaning preservation and transfer accuracy across all the six style transfer tasks. The data and code is located at https://github.com/tag-and-generate.

pdf bib
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
Zhiqing Sun | Hongkun Yu | Xiaodan Song | Renjie Liu | Yiming Yang | Denny Zhou
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be deployed to resource-limited mobile devices. In this paper, we propose MobileBERT for compressing and accelerating the popular BERT model. Like the original BERT, MobileBERT is task-agnostic, that is, it can be generically applied to various downstream NLP tasks via simple fine-tuning. Basically, MobileBERT is a thin version of BERT_LARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. To train MobileBERT, we first train a specially designed teacher model, an inverted-bottleneck incorporated BERT_LARGE model. Then, we conduct knowledge transfer from this teacher to MobileBERT. Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE while achieving competitive results on well-known benchmarks. On the natural language inference tasks of GLUE, MobileBERT achieves a GLUE score of 77.7 (0.6 lower than BERT_BASE), and 62 ms latency on a Pixel 4 phone. On the SQuAD v1.1/v2.0 question answering task, MobileBERT achieves a dev F1 score of 90.0/79.2 (1.5/2.1 higher than BERT_BASE).

pdf bib
A Re-evaluation of Knowledge Graph Completion Methods
Zhiqing Sun | Shikhar Vashishth | Soumya Sanyal | Partha Talukdar | Yiming Yang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs. A vast number of state-of-the-art KGC techniques have got published at top conferences in several research fields, including data mining, machine learning, and natural language processing. However, we notice that several recent papers report very high performance, which largely outperforms previous state-of-the-art methods. In this paper, we find that this can be attributed to the inappropriate evaluation protocol used by them and propose a simple evaluation protocol to address this problem. The proposed protocol is robust to handle bias in the model, which can substantially affect the final results. We conduct extensive experiments and report performance of several existing methods using our protocol. The reproducible code has been made publicly available.

pdf bib
Predicting Performance for Natural Language Processing Tasks
Mengzhou Xia | Antonios Anastasopoulos | Ruochen Xu | Yiming Yang | Graham Neubig
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Given the complexity of combinations of tasks, languages, and domains in natural language processing (NLP) research, it is computationally prohibitive to exhaustively test newly proposed models on each possible experimental setting. In this work, we attempt to explore the possibility of gaining plausible judgments of how well an NLP model can perform under an experimental setting, without actually training or testing the model. To do so, we build regression models to predict the evaluation score of an NLP experiment given the experimental settings as input. Experimenting on~9 different NLP tasks, we find that our predictors can produce meaningful predictions over unseen languages and different modeling architectures, outperforming reasonable baselines as well as human experts. %we represent experimental settings using an array of features. Going further, we outline how our predictor can be used to find a small subset of representative experiments that should be run in order to obtain plausible predictions for all other experimental settings.

pdf bib
On the Sentence Embeddings from Pre-trained Language Models
Bohan Li | Hao Zhou | Junxian He | Mingxuan Wang | Yiming Yang | Lei Li
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We first reveal the theoretical connection between the masked language model pre-training objective and the semantic similarity task theoretically, and then analyze the BERT sentence embeddings empirically. We find that BERT always induces a non-smooth anisotropic semantic space of sentences, which harms its performance of semantic similarity. To address this issue, we propose to transform the anisotropic sentence embedding distribution to a smooth and isotropic Gaussian distribution through normalizing flows that are learned with an unsupervised objective. Experimental results show that our proposed BERT-flow method obtains significant performance gains over the state-of-the-art sentence embeddings on a variety of semantic textual similarity tasks. The code is available at https://github.com/bohanli/BERT-flow.

2019

pdf bib
A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
Bohan Li | Junxian He | Graham Neubig | Taylor Berg-Kirkpatrick | Yiming Yang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are trained with the evidence lower bound (ELBO) as a surrogate objective to the intractable marginal data likelihood. This approach to training yields unstable results, frequently leading to a disastrous local optimum known as posterior collapse. In this paper, we investigate a simple fix for posterior collapse which yields surprisingly effective results. The combination of two known heuristics, previously considered only in isolation, substantially improves held-out likelihood, reconstruction, and latent representation learning when compared with previous state-of-the-art methods. More interestingly, while our experiments demonstrate superiority on these principle evaluations, our method obtains a worse ELBO. We use these results to argue that the typical surrogate objective for VAEs may not be sufficient or necessarily appropriate for balancing the goals of representation learning and data distribution modeling.

pdf bib
DEFT: A corpus for definition extraction in free- and semi-structured text
Sasha Spala | Nicholas A. Miller | Yiming Yang | Franck Dernoncourt | Carl Dockhorn
Proceedings of the 13th Linguistic Annotation Workshop

Definition extraction has been a popular topic in NLP research for well more than a decade, but has been historically limited to well-defined, structured, and narrow conditions. In reality, natural language is messy, and messy data requires both complex solutions and data that reflects that reality. In this paper, we present a robust English corpus and annotation schema that allows us to explore the less straightforward examples of term-definition structures in free and semi-structured text.

pdf bib
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context
Zihang Dai | Zhilin Yang | Yiming Yang | Jaime Carbonell | Quoc Le | Ruslan Salakhutdinov
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-level recurrence mechanism and a novel positional encoding scheme. Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem. As a result, Transformer-XL learns dependency that is 80% longer than RNNs and 450% longer than vanilla Transformers, achieves better performance on both short and long sequences, and is up to 1,800+ times faster than vanilla Transformers during evaluation. Notably, we improve the state-of-the-art results of bpc/perplexity to 0.99 on enwiki8, 1.08 on text8, 18.3 on WikiText-103, 21.8 on One Billion Word, and 54.5 on Penn Treebank (without finetuning). When trained only on WikiText-103, Transformer-XL manages to generate reasonably coherent, novel text articles with thousands of tokens. Our code, pretrained models, and hyperparameters are available in both Tensorflow and PyTorch.

2018

pdf bib
Low-resource Cross-lingual Event Type Detection via Distant Supervision with Minimal Effort
Aldrian Obaja Muis | Naoki Otani | Nidhi Vyas | Ruochen Xu | Yiming Yang | Teruko Mitamura | Eduard Hovy
Proceedings of the 27th International Conference on Computational Linguistics

The use of machine learning for NLP generally requires resources for training. Tasks performed in a low-resource language usually rely on labeled data in another, typically resource-rich, language. However, there might not be enough labeled data even in a resource-rich language such as English. In such cases, one approach is to use a hand-crafted approach that utilizes only a small bilingual dictionary with minimal manual verification to create distantly supervised data. Another is to explore typical machine learning techniques, for example adversarial training of bilingual word representations. We find that in event-type detection task—the task to classify [parts of] documents into a fixed set of labels—they give about the same performance. We explore ways in which the two methods can be complementary and also see how to best utilize a limited budget for manual annotation to maximize performance gain.

pdf bib
Unsupervised Cross-lingual Transfer of Word Embedding Spaces
Ruochen Xu | Yiming Yang | Naoki Otani | Yuexin Wu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem would benefit many downstream tasks such as to translate text classification models from resource-rich languages (e.g. English) to low-resource languages. Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages. This paper proposes an unsupervised learning approach that does not require any cross-lingual labeled data. Given two monolingual word embedding spaces for any language pair, our algorithm optimizes the transformation functions in both directions simultaneously based on distributional matching as well as minimizing the back-translation losses. We use a neural network implementation to calculate the Sinkhorn distance, a well-defined distributional similarity measure, and optimize our objective through back-propagation. Our evaluation on benchmark datasets for bilingual lexicon induction and cross-lingual word similarity prediction shows stronger or competitive performance of the proposed method compared to other state-of-the-art supervised and unsupervised baseline methods over many language pairs.

2017

pdf bib
Cross-lingual Distillation for Text Classification
Ruochen Xu | Yiming Yang
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Cross-lingual text classification(CLTC) is the task of classifying documents written in different languages into the same taxonomy of categories. This paper presents a novel approach to CLTC that builds on model distillation, which adapts and extends a framework originally proposed for model compression. Using soft probabilistic predictions for the documents in a label-rich language as the (induced) supervisory labels in a parallel corpus of documents, we train classifiers successfully for new languages in which labeled training data are not available. An adversarial feature adaptation technique is also applied during the model training to reduce distribution mismatch. We conducted experiments on two benchmark CLTC datasets, treating English as the source language and German, French, Japan and Chinese as the unlabeled target languages. The proposed approach had the advantageous or comparable performance of the other state-of-art methods.

pdf bib
RACE: Large-scale ReAding Comprehension Dataset From Examinations
Guokun Lai | Qizhe Xie | Hanxiao Liu | Yiming Yang | Eduard Hovy
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We present RACE, a new dataset for benchmark evaluation of methods in the reading comprehension task. Collected from the English exams for middle and high school Chinese students in the age range between 12 to 18, RACE consists of near 28,000 passages and near 100,000 questions generated by human experts (English instructors), and covers a variety of topics which are carefully designed for evaluating the students’ ability in understanding and reasoning. In particular, the proportion of questions that requires reasoning is much larger in RACE than that in other benchmark datasets for reading comprehension, and there is a significant gap between the performance of the state-of-the-art models (43%) and the ceiling human performance (95%). We hope this new dataset can serve as a valuable resource for research and evaluation in machine comprehension. The dataset is freely available at http://www.cs.cmu.edu/~glai1/data/race/and the code is available at https://github.com/qizhex/RACE_AR_baselines.

2016

pdf bib
Leveraging Multilingual Training for Limited Resource Event Extraction
Andrew Hsi | Yiming Yang | Jaime Carbonell | Ruochen Xu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Event extraction has become one of the most important topics in information extraction, but to date, there is very limited work on leveraging cross-lingual training to boost performance. We propose a new event extraction approach that trains on multiple languages using a combination of both language-dependent and language-independent features, with particular focus on the case where target domain training data is of very limited size. We show empirically that multilingual training can boost performance for the tasks of event trigger extraction and event argument extraction on the Chinese ACE 2005 dataset.

2004

pdf bib
Customizing Parallel Corpora at the Document Level
Monica Rogati | Yiming Yang
Proceedings of the ACL Interactive Poster and Demonstration Sessions

pdf bib
Learning Table Extraction from Examples
Ashwin Tengli | Yiming Yang | Nian Li Ma
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

2003

pdf bib
Unsupervised Learning of Arabic Stemming Using a Parallel Corpus
Monica Rogati | Scott McCarley | Yiming Yang
Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics

1992

pdf bib
A Linear Least Squares Fit Mapping Method for Information Retrieval From Natural Language Texts
Yiming Yang | Christopher G. Chute
COLING 1992 Volume 2: The 14th International Conference on Computational Linguistics

1984

pdf bib
Use of Heuristic Knowledge in Chinese Language Analysis
Yiming Yang | Toyoaki Nishida | Shuji Doshita
10th International Conference on Computational Linguistics and 22nd Annual Meeting of the Association for Computational Linguistics