More Like this

1. Which Evaluations Uncover Sense Representations that Actually Make Sense?

   Jordan Boyd-Graber, Fenfei Guo (May 2020, Proceedings of the 12th Language Resources and Evaluation Conference)

   null (Ed.)

   Text representations are critical for modern natural language processing. One form of text representation, sense-specific embeddings, reflect a word’s sense in a sentence better than single-prototype word embeddings tied to each type. However, existing sense representations are not uniformly better: although they work well for computer-centric evaluations, they fail for human-centric tasks like inspecting a language’s sense inventory. To expose this discrepancy, we propose a new coherence evaluation for sense embeddings. We also describe a minimal model (Gumbel Attention for Sense Induction) optimized for discovering interpretable sense representations that are more coherent than existing sense embeddings. 

   more » « less
2. Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings

   Manzini, Thomas; Lim, Yao Chong; Tsvetkov, Yulia; Black, Alan W (June 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL))

   Online texts—across genres, registers, domains, and styles—are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks. 

   more » « less
3. Dict-BERT: Enhancing Language Model Pre-training with Dictionary

   https://doi.org/10.18653/v1/2022.findings-acl.150  

   Yu, Wenhao; Zhu, Chenguang; Fang, Yuwei; Yu, Donghan; Wang, Shuohang; Xu, Yichong; Zeng, Michael; Jiang, Meng (January 2022, Findings of the Association for Computational Linguistics: ACL 2022)

   Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word representations highly depends on word frequency, which usually follows a heavy-tailed distributions in the pre-training corpus. Therefore, the embeddings of rare words on the tail are usually poorly optimized. In this work, we focus on enhancing language model pre-training by leveraging definitions of the rare words in dictionaries (e.g., Wiktionary). To incorporate a rare word definition as a part of input, we fetch its definition from the dictionary and append it to the end of the input text sequence. In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary. We evaluate the proposed Dict-BERT model on the language understanding benchmark GLUE and eight specialized domain benchmark datasets. Extensive experiments demonstrate that Dict-BERT can significantly improve the understanding of rare words and boost model performance on various NLP downstream tasks. 

   more » « less
4. On the Power of Pre-Trained Text Representations: Models and Applications in Text Mining

   https://doi.org/10.1145/3447548.3470810  

   Meng, Yu; Huang, Jiaxin; Zhang, Yu; Han, Jiawei (August 2021, KDD'21:The 27th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, August 14-18, 2021)

   null (Ed.)

   Recent years have witnessed the enormous success of text representation learning in a wide range of text mining tasks. Earlier word embedding learning approaches represent words as fixed low-dimensional vectors to capture their semantics. The word embeddings so learned are used as the input features of task-specific models. Recently, pre-trained language models (PLMs), which learn universal language representations via pre-training Transformer-based neural models on large-scale text corpora, have revolutionized the natural language processing (NLP) field. Such pre-trained representations encode generic linguistic features that can be transferred to almost any text-related applications. PLMs outperform previous task-specific models in many applications as they only need to be fine-tuned on the target corpus instead of being trained from scratch. In this tutorial, we introduce recent advances in pre-trained text embeddings and language models, as well as their applications to a wide range of text mining tasks. Specifically, we first overview a set of recently developed self-supervised and weakly-supervised text embedding methods and pre-trained language models that serve as the fundamentals for downstream tasks. We then present several new methods based on pre-trained text embeddings and language models for various text mining applications such as topic discovery and text classification. We focus on methods that are weakly-supervised, domain-independent, language-agnostic, effective and scalable for mining and discovering structured knowledge from large-scale text corpora. Finally, we demonstrate with real world datasets how pre-trained text representations help mitigate the human annotation burden and facilitate automatic, accurate and efficient text analyses. 

   more » « less
5. When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People?

   https://doi.org/10.18653/v1/2020.acl-main.405  

   Joseph, Kenneth; Morgan, Jonathan (January 2020, Association for Computational Linguistics)

   null (Ed.)

   Social biases are encoded in word embeddings. This presents a unique opportunity to study society historically and at scale, and a unique danger when embeddings are used in downstream applications. Here, we investigate the extent to which publicly-available word embeddings accurately reflect beliefs about certain kinds of people as measured via traditional survey methods. We find that biases found in word embeddings do, on average, closely mirror survey data across seventeen dimensions of social meaning. However, we also find that biases in embeddings are much more reflective of survey data for some dimensions of meaning (e.g. gender) than others (e.g. race), and that we can be highly confident that embedding-based measures reflect survey data only for the most salient biases. 

   more » « less