We show that BERT (Devlin et al., 2018) is a Markov random field language model. This formulation gives way to a natural procedure to sample sentences from BERT. We generate from BERT and find that it can produce high-quality, fluent generations. Compared to the generations of a traditional left-to-right language model, BERT generates sentences that are more diverse but of slightly worse quality.
Hebrew University of Jerusalem（希伯来大学）；University of Utah（犹他大学）；Georgetown University（乔治城大学）
We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses. By inducing a contextualized "pseudoword" as a stand-in for a static embedding in the input layer, and then performing masked prediction of a word in the sentence, we are able to investigate the geometry of the BERT-space in a controlled manner around individual instances. Using our method on a set of carefully constructed sentences targeting ambiguous English words, we find substantial regularity in…
School of Computer Science, Tel Aviv University（特拉维夫大学计算机科学学院）；Allen Institute for AI（艾伦人工智能研究所）
Large pre-trained language models have been shown to encode large amounts of world and commonsense knowledge in their parameters, leading to substantial interest in methods for extracting that knowledge. In past work, knowledge was extracted by taking manually-authored queries and gathering paraphrases for them using a separate pipeline. In this work, we propose a method for automatically rewriting queries into "BERTese", a paraphrase query that is directly optimized towards better knowledge extraction. To encourage meaningful rewrites, we add auxiliary loss functions that encourage the query …
National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China（中国科学技术大学语音及语言信息处理国家工程实验室）；State Key Laboratory of Cognitive Intelligence, iFLYTEK Research（科大讯飞研究院认知智能国家重点实验室）
In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the speaker change information, which is an important and intrinsic property of multi-turn dialogues. Furthermore, a speaker-aware disentanglement strategy is proposed to tackle the entangled dialogues. This strategy selects a small number of most important utterances as the filtered context according to the speakers' information in them. Finally, domain adapta…
University of Science and Technology of China（中国科学技术大学）；Microsoft（微软）
Recently, various neural models for multi-party conversation (MPC) have achieved impressive improvements on a variety of tasks such as addressee recognition, speaker identification and response prediction. However, these existing methods on MPC usually represent interlocutors and utterances individually and ignore the inherent complicated structure in MPC which may provide crucial interlocutor and utterance semantics and would enhance the conversation understanding process. To this end, we present MPC-BERT, a pre-trained model for MPC understanding that considers learning who says what to whom…
Jamia Millia Islamia（贾米亚·米利亚伊斯兰大学）；Aligarh Muslim University（阿里加尔穆斯林大学）
Language identification of social media text has been an interesting problem of study in recent years. Social media messages are predominantly in code mixed in non-English speaking states. Prior knowledge by pre-training contextual embeddings have shown state of the art results for a range of downstream tasks. Recently, models such as BERT have shown that using a large amount of unlabeled data, the pretrained language models are even more beneficial for learning common language representations. Extensive experiments exploiting transfer learning and fine-tuning BERT models to identify language …
Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal behaviors to generate a meaningful representation of the conversation. In this work, we propose to dissect SLU into three representative properties:conversational (disfluency, pause, overtalk), channel (speaker-type, turn-tasks) and ASR (insertion, deletion,substitution). We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investi…
Beijing University of Posts and Telecommunications（北京邮电大学）；Didi Research Institute, Didi Chuxing（滴滴出行滴滴研究院）
In the field of car evaluation, more and more netizens choose to express their opinions on the Internet platform, and these comments will affect the decision-making of buyers and the trend of car word-of-mouth. As an important branch of natural language processing (NLP), sentiment analysis provides an effective research method for analyzing the sentiment types of massive car review texts. However, due to the lexical professionalism and large text noise of review texts in the automotive field, when a general sentiment analysis model is applied to car reviews, the accuracy of the model will be p…
The appearance of complex attention-based language models such as BERT, Roberta or GPT-3 has allowed to address highly complex tasks in a plethora of scenarios. However, when applied to specific domains, these models encounter considerable difficulties. This is the case of Social Networks such as Twitter, an ever-changing stream of information written with informal and complex language, where each message requires careful evaluation to be understood even by humans given the important role that context plays. Addressing tasks in this domain through Natural Language Processing involves severe ch…
Southeast University（东南大学）；Ulm University（乌尔姆大学）；Mercedes-Benz Research & Development（梅赛德斯-奔驰研发中心）
This paper introduces a natural language understanding (NLU) framework for argumentative dialogue systems in the information-seeking and opinion building domain. The proposed framework consists of two sub-models, namely intent classifier and argument similarity. Intent classifier model stacks BiLSTM with attention mechanism on top of the pre-trained BERT model and fine-tune the model for recognizing the user intent, whereas the argument similarity model employs BERT+BiLSTM for identifying system arguments the user refers to in his or her natural language utterances. Our model is evaluated in a…
Graduate School of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术研究生院）；School of Engineering, Hokkaido University（北海道大学工程学院）；Faculty of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术学院）
There are many discussions held during political meetings, and a large number of utterances for various topics is included in their transcripts. We need to read all of them if we want to follow speakers\' intentions or opinions about a given topic. To avoid such a costly and time-consuming process to grasp often longish discussions, NLP researchers work on generating concise summaries of utterances. Summarization subtask in QA Lab-PoliInfo-2 task of the NTCIR-15 addresses this problem for Japanese utterances in assembly minutes, and our team (SKRA) participated in this subtask. As a first step…
In the last few years, the release of BERT, a multilingual transformer based model, has taken the NLP community by storm. BERT-based models have achieved state-of-the-art results on various NLP tasks, including dialog tasks. One of the limitation of BERT is the lack of ability to handle long text sequence. By default, BERT has a maximum wordpiece token sequence length of 512. Recently, there has been renewed interest to tackle the BERT limitation to handle long text sequences with the addition of new self-attention based architectures. However, there has been little to no research on the impac…
Peking University（北京大学）；Shanghai Jiao Tong University（上海交通大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
We conduct a thorough study to diagnose the behaviors of pre-trained language encoders (ELMo, BERT, and RoBERTa) when confronted with natural grammatical errors. Specifically, we collect real grammatical errors from non-native speakers and conduct adversarial attacks to simulate these errors on clean text data. We use this approach to facilitate debugging models on downstream applications. Results confirm that the performance of all tested models is affected but the degree of impact varies. To interpret model behaviors, we further design a linguistic acceptability task to reveal their abilitie…
University of Surrey（萨里大学）；ETH Zurich（苏黎世联邦理工学院）；University of Lausanne（洛桑大学）；University of Zurich（苏黎世大学）；University of Konstanz（康斯坦茨大学）；University of St. Gallen（圣加仑大学）
Many processes in psychology are complex, such as dyadic interactions between two interacting partners (e.g. patient-therapist, intimate relationship partners). Nevertheless, many basic questions about interactions are difficult to investigate because dyadic processes can be within a person and between partners, they are based on multimodal aspects of behavior and unfold rapidly. Current analyses are mainly based on the behavioral coding method, whereby human coders annotate behavior based on a coding schema. But coding is labor-intensive, expensive, slow, focuses on few modalities. Current ap…
New York University（纽约大学）；IBM Research AI（IBM研究院人工智能实验室）
A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach presents some challenges. First, since speech can be considered as personally identifiable information, in some cases only automatic speech recognition (ASR) transcripts are accessible. Second, intent-labeled speech data is scarce. To address the first challenge, we propose a novel system that can predict intents from flexible types of inputs: speech, ASR transcri…
Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks including abstractive summarization. Existing approaches in dialogue summarization focus on incorporating a large language model into summarization task trained on large-scale corpora consisting of news articles rather than dialogues of multiple speakers. In this paper, we introduce self-supervised methods to compensate shortcomings to train a dialogue summari…
The NTNU System at the S&I Challenge 2025 SLA Open Track
National Taiwan Normal University（国立台湾师范大学）；Department of Computer Science and Information Engineering（计算机科学与信息工程系）；Institute of AI Interdisciplinary Applied Technology（人工智能跨学科应用技术研究所）
Institute of Artificial Intelligence Research, Qihoo of Beijing Science and Technology Co. Ltd.（北京奇虎科技有限公司人工智能研究院）
Historically lower-level tasks such as automatic speech recognition (ASR) and speaker identification are the main focus in the speech field. Interest has been growing in higher-level spoken language understanding (SLU) tasks recently, like sentiment analysis (SA). However, improving performances on SLU tasks remains a big challenge. Basically, there are two main methods for SLU tasks: (1) Two-stage method, which uses a speech model to transfer speech to text, then uses a language model to get the results of downstream tasks; (2) One-stage method, which just fine-tunes a pre-trained speech mode…
The recent success of large pre-trained language models such as BERT and GPT-2 has suggested the effectiveness of incorporating language priors in downstream dialog generation tasks. However, the performance of pre-trained models on the dialog task is not as optimal as expected. In this paper, we propose a Pre-trained Role Alternating Language model (PRAL), designed specifically for task-oriented conversational systems. We adopted (Wu et al., 2019) that models two speakers separately. We also design several techniques, such as start position randomization, knowledge distillation, and history d…
University of Guilan（吉兰大学）；Alzahra University（扎赫拉大学）；Shahid Beheshti University（沙希德·贝赫什提大学）
Persian Poetry has consistently expressed its philosophy, wisdom, speech, and rationale on the basis of its couplets, making it an enigmatic language on its own to both native and non-native speakers. Nevertheless, the notice able gap between Persian prose and poem has left the two pieces of literature medium-less. Having curated a parallel corpus of prose and their equivalent poems, we introduce a novel Neural Machine Translation (NMT) approach to translate prose to ancient Persian poetry using transformer-based Language Models in an extremely low-resource setting. More specifically, we train…
