Sequence to sequence models attempt to capture the correlation between all the words in the input and output sequences. While this is quite useful for machine translation where the correlation among the words is indeed quite strong, it becomes problematic for conversation modelling where the correlation is often at a much abstract level. In contrast, humans tend to focus on the essential concepts discussed in the conversation context and generate responses accordingly. In this paper, we attempt to mimic this response generating mechanism by learning the essential concepts in the context and response in an unsupervised manner. The proposed model, referred to as Mask \& Focus maps the input context to a sequence of concepts which are then used to generate the response concepts. Together, the context and the response concepts generate the final response. In order to learn context concepts from the training data automatically, we \emph{mask} words in the input and observe the effect of masking on response generation. We train our model to learn those response concepts that have high mutual information with respect to the context concepts, thereby guiding the model to \emph{focus} on the context concepts. Mask \& Focus achieves significant improvement over the existing baselines in several established metrics for dialogues.
Nanjing University of Science and Technology（南京理工大学）；Microsoft Research（微软研究院）
Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the success of BERT, we propose MAsked Sequence to Sequence pre-training (MASS) for the encoder-decoder based language generation tasks. MASS adopts the encoder-decoder framework to reconstruct a sentence fragment given the remaining part of the sentence: its encoder takes a sentence with randomly masked fragment (several consecutive tokens) as input, and its decoder tries to predict…
Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations. One of the most intractable problems of conversational text-to-SQL is modelling the semantics of multi-turn queries and gathering the proper information required for the current query. This paper shows that explicitly modelling the semantic changes by adding each turn and the summarization of the whole context can bring better performance on converting conversational queries into SQLs. In particular, we propose two conversational modelling …
LTCI, Telecom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）；IBM GBS France（法国IBM全球企业服务部）；IBM Zurich（苏黎世IBM）
The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents. Accurately predicting DAs requires a precise modeling of both the conversation and the global tag dependencies. We leverage seq2seq approaches widely adopted in Neural Machine Translation (NMT) to improve the modelling of tag sequentiality. Seq2seq models are known to learn complex global dependencies while currently proposed approaches using linear conditional random fields (CRF) only model local tag dependencies. In this work, we introduce a seq2seq model tai…
Carnegie Mellon University（卡内基梅隆大学）；Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）；Zendrive Inc（Zendrive公司）
Modelling persuasion strategies as predictors of task outcome has several real-world applications and has received considerable attention from the computational linguistics community. However, previous research has failed to account for the resisting strategies employed by an individual to foil such persuasion attempts. Grounded in prior literature in cognitive and social psychology, we propose a generalised framework for identifying resisting strategies in persuasive conversations. We instantiate our framework on two distinct datasets comprising persuasion and negotiation conversations. We al…
IBM Research Zurich（IBM研究院苏黎世分部）；Telecom Paris（巴黎电信学院）；IBM France（IBM法国分部）
The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents. Accurately predicting DAs requires a precise modeling of both the conversation and the global tag dependencies. We leverage seq2seq approaches widely adopted in Neural Machine Translation (NMT) to improve the modelling of tag sequentiality. Seq2seq models are known to learn complex global dependencies while currently proposed approaches using linear conditional random fields (CRF) only model local tag dependencies. In this work, we introduce a seq2seq model tai…
School of Computer and Communication Sciences（计算机与通信科学学院）；École polytechnique fédérale de Lausanne（洛桑联邦理工学院）
Open-domain conversational agents or chatbots are becoming increasingly popular in the natural language processing community. One of the challenges is enabling them to converse in an empathetic manner. Current neural response generation methods rely solely on end-to-end learning from large scale conversation data to generate dialogues. This approach can produce socially unacceptable responses due to the lack of large-scale quality data used to train the neural models. However, recent work has shown the promise of combining dialogue act/intent modelling and neural response generation. This hybr…
Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking
ADAPT Centre, Trinity College Dublin（都柏林圣三一学院ADAPT中心）；ADAPT Centre, University College Dublin（都柏林大学学院ADAPT中心）；ADAPT Center, Trinity College Dublin（都柏林圣三一学院ADAPT中心）
The impact of user satisfaction in policy learning task-oriented dialogue systems has long been a subject of research interest. Most current models for estimating the user satisfaction either (i) treat out-of-context short-texts, such as product reviews, or (ii) rely on turn features instead of on distributed semantic representations. In this work we adopt deep neural networks that use distributed semantic representation learning for estimating the user satisfaction in conversations. We evaluate the impact of modelling context length in these networks. Moreover, we show that the proposed hiera…
Dialog modelling faces a difficult trade-off. Models are trained on a large amount of text, yet their responses need to be limited to a desired scope and style of a dialog agent. Because the datasets used to achieve the former contain language that is not compatible with the latter, pre-trained dialog models are fine-tuned on smaller curated datasets. However, the fine-tuning process robs them of the ability to produce diverse responses, eventually reducing them to dull conversation partners. In this paper we investigate if prompting can mitigate the above trade-off. Specifically, we experimen…
While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the absence of linguistic context. In this paper, we explore how the contextualised embeddings predicted by BERT can be used to produce high-quality word vectors for such domains, in particular related to knowledge base completion, where our focus is on capturing the semantic properties of nouns. We find that a simple strategy of averaging the contextualised emb…
ConText at WASSA 2024 Empathy and Personality Shared Task: History-Dependent Embedding Utterance Representations for Empathy and Emotion Prediction in Conversations
INESC-ID；Instituto Superior Técnico, University of Lisbon（里斯本大学高级技术学院）；Faculdade de Letras, University of Lisbon（里斯本大学文学院）
iFLYTEK Research, Hefei（科大讯飞研究院（合肥））；Department of Electrical and Computer Engineering, Queen’s University（女王大学电气与计算机工程系）
We present our work on Track 2 in the Dialog System Technology Challenges 7 (DSTC7). The DSTC7-Track 2 aims to evaluate the response generation of fully data-driven conversation models in knowledge-grounded settings, which provides the contextual-relevant factual texts. The Sequenceto-Sequence models have been widely used for end-to-end generative conversation modelling and achieved impressive results. However, they tend to output dull and repeated responses in previous studies. Our work aims to promote the diversity for end-to-end conversation response generation, which follows a two-stage pi…
Utterance-level emotion recognition (ULER) is a significant research topic for understanding human behaviors and developing empathetic chatting machines in the artificial intelligence area. Unlike traditional text classification problem, this task is supported by a limited number of datasets, among which most contain inadequate conversations or speeches. Such a data scarcity issue limits the possibility of training larger and more powerful models for this task. Witnessing the success of transfer learning in natural language process (NLP), we propose to pre-train a context-dependent encoder (Co…
Dwarkadas J. Sanghvi College of Engineering（德瓦卡达斯·J·桑格维工程学院）
Social media networks and chatting platforms often use an informal version of natural text. Adversarial spelling attacks also tend to alter the input text by modifying the characters in the text. Normalizing these texts is an essential step for various applications like language translation and text to speech synthesis where the models are trained over clean regular English language. We propose a new robust model to perform text normalization. Our system uses the BERT language model to predict the masked words that correspond to the unnormalized words. We propose two unique masking strategies …
Radboud University Nijmegen（奈梅亨拉德堡德大学）；Delft University of Technology（代尔夫特理工大学）
Background music in social interaction settings can hinder conversation. Yet, little is known of how specific properties of music impact speech processing. This paper addresses this knowledge gap by investigating 1) whether the masking effect of background music with lyrics is larger than that of music without lyrics, and 2) whether the masking effect is larger for more complex music. To answer these questions, a word identification experiment was run in which Dutch participants listened to Dutch CVC words embedded in stretches of background music in two conditions, with and without lyrics, an…
