Word similarity is broadly used in many applications, such as information retrieval, information extraction, text classification, word sense disambiguation, example -based machine translation, etc. There are two different methods used to compute similarity: one is based on ontology or a semantic taxonomy; the other is based on collocations of words in a corpus. As a lexical knowledgebase with rich semantic information, How-net has been employed in various researches. Unlike other thesauri, such as WordNet and Tongyici Cilin, in which word similarity is defined based on the distance between words in a semantic taxonomy tree, How-net defines a word in a complicated multi-dimensional knowledge description language. As a result, a series of problems arise in the process of word similarity computation using How-net. The difficulties are outlined below: 1. The description of each word consists of a group of sememes. For example, the Chinese word “暗箱(camera obscura)” is described as: “part|部件, #TakePicture|拍攝, %tool|用具 , body|身”, and the Chinese word “寫信 (write a letter)” is described as: “write|寫, ContentProduct=letter|信件”; 2. The meaning of a word is not a simple combination of these sememes. Sememes are organized using a specific knowledge description language. To meet these challenges, our work includes: 1. A study on the How-net knowledge description language. We rewrite the How-net definition of a word in a more structural format, using the abstract data structure of set and feature structure. 2. A study on the algorithm used to compute word similarity based on How-net. The similarity between sememes, that between sets , and that between feature structures are given. To compute the similarity between two sememes, we

/pdf/ji-yu-zhi-wang-de-ci-hui-yu-yi-xiang-si-du-ji-suan-word-3q2xf1mp2c.pdf

基於《知網》的辭彙語義相似度計算 (Word Similarity Computing Based on How-net).

The goal-oriented dialogue system needs to be optimized for tracking the dialogue flow and carrying out an effective conversation under various situations to meet the user goal. The traditional approach to build such a dialogue system is to take a pipelined modular architecture, where its modules are optimized individually. However, such an optimization scheme does not necessarily yield the overall performance improvement of the whole system. On the other hand, end-to-end dialogue systems with monolithic neural architecture are often trained only with input-output utterances, without taking into account the entire annotations available in the corpus. This scheme makes it difficult for goal-oriented dialogues where the system needs to integrate with external systems or to provide interpretable information about why the system generated a particular response. In this paper, we present an end-to-end neural architecture for dialogue systems that addresses both challenges above. In the human evaluation, our dialogue system achieved the success rate of 68.32%, the language understanding score of 4.149, and the response appropriateness score of 4.287, which ranked the system at the top position in the end-to-end multi-domain dialogue system task in the 8th dialogue systems technology challenge (DSTC8).

/pdf/end-to-end-neural-pipeline-for-goal-oriented-dialogue-20rebwfhzw.pdf

End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2.

This paper presents a new method SOLOIST, which uses transfer learning to efficiently build task-oriented dialog systems at scale. We parameterize a dialog system using a Transformer-based auto-regressive language model, which subsumes different dialog modules (e.g., state tracker, dialog policy, response generator) into a single neural model. We pre-train, on large heterogeneous dialog corpora, a large-scale Transformer model which can generate dialog responses grounded in user goals and real-world knowledge for task completion. The pre-trained model can be efficiently adapted to accomplish a new dialog task with a handful of task-specific dialogs via machine teaching. Our experiments demonstrate that (i) SOLOIST creates new state-of-the-art results on two well-known benchmarks, CamRest and MultiWOZ, (ii) in the few-shot learning setting, the dialog systems developed by SOLOIST significantly outperform those developed by existing methods, and (iii) the use of machine teaching substantially reduces the labeling cost. We will release our code and pre-trained models for reproducible research.

SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model

Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due to inherent shortcomings: (a) What exactly does a user like? (b) Why does a user like an item? The shortcomings are due to the way that static models learn user preference, i.e., without explicit instructions and active feedback from users. The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally. In a CRS, users and the system can dynamically communicate through natural language interactions, which provide unprecedented opportunities to explicitly obtain the exact preference of users. Considerable efforts, spread across disparate settings and applications, have been put into developing CRSs. Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs. We summarize the key challenges of developing CRSs in five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding and generation. (4) Exploitation-exploration trade-offs. (5) Evaluation and user simulation. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI). Based on these research directions, we discuss some future challenges and opportunities. We provide a road map for researchers from multiple communities to get started in this area. We hope this survey can help to identify and address challenges in CRSs and inspire future research.

Advances and challenges in conversational recommender systems: A survey

We present a new method SOLOIST that uses transfer learning and machine
teaching to build task bots at scale. We parameterize classical modular
task-oriented dialog systems using a Transformer-based auto-regressive language
model, which subsumes different dialog modules into a single neural model. We
pre-train, on heterogeneous dialog corpora, a task-grounded response generation
model, which can generate dialog responses grounded in user goals and
real-world knowledge for task completion. The pre-trained model can be
efficiently adapted to accomplish new tasks with a handful of task-specific
dialogs via machine teaching, where training samples are generated by human
teachers interacting with the system. Experiments show that (i) SOLOIST creates
new state-of-the-art on well-studied task-oriented dialog benchmarks, including
CamRest676 and MultiWOZ; (ii) in the few-shot fine-tuning settings, SOLOIST
significantly outperforms existing methods, and (iii) the use of machine
teaching substantially reduces the labeling cost of fine-tuning. The
pre-trained models and codes are available at https://aka.ms/soloist.

SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching

End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a single-module model to generate responses for complex dialogue contexts. However, no model consistently outperforms the others in all cases. We propose a neural Modular Task-oriented Dialogue System(MTDS) framework, in which a few expert bots are combined to generate the response for a given dialogue context. MTDS consists of a chair bot and several expert bots. Each expert bot is specialized for a particular situation, e.g., one domain, one type of action of a system, etc. The chair bot coordinates multiple expert bots and adaptively selects an expert bot to generate the appropriate response. We further propose a Token-level Mixture-of-Expert (TokenMoE) model to implement MTDS, where the expert bots predict multiple tokens at each timestamp and the chair bot determines the final generated token by fully taking into consideration the outputs of all expert bots. Both the chair bot and the expert bots are jointly trained in an end-to-end fashion. To verify the effectiveness of TokenMoE, we carry out extensive experiments on a benchmark dataset. Compared with the baseline using a single-module model, our TokenMoE improves the performance by 8.1% of inform rate and 0.8% of success rate.

A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts

There is increasing interest in developing personalized Task-oriented Dialogue Systems (TDSs). Previous work on personalized TDSs often assumes that complete user profiles are available for most or even all users. This is unrealistic because (1) not everyone is willing to expose their profiles due to privacy concerns; and (2) rich user profiles may involve a large number of attributes (e.g., gender, age, tastes, . . .). In this paper, we study personalized TDSs without assuming that user profiles are complete. We propose a Cooperative Memory Network (CoMemNN) that has a novel mechanism to gradually enrich user profiles as dialogues progress and to simultaneously improve response selection based on the enriched profiles. CoMemNN consists of two core modules: User Profile Enrichment (UPE) and Dialogue Response Selection (DRS). The former enriches incomplete user profiles by utilizing collaborative information from neighbor users as well as current dialogues. The latter uses the enriched profiles to update the current user query so as to encode more useful information, based on which a personalized response to a user request is selected. 
We conduct extensive experiments on the personalized bAbI dialogue benchmark datasets. We find that CoMemNN is able to enrich user profiles effectively, which results in an improvement of 3.06% in terms of response selection accuracy compared to state-of-the-art methods. We also test the robustness of CoMemNN against incompleteness of user profiles by randomly discarding attribute values from user profiles. Even when discarding 50% of the attribute values, CoMemNN is able to match the performance of the best performing baseline without discarding user profiles, showing the robustness of CoMemNN.

/pdf/a-cooperative-memory-network-for-personalized-task-oriented-4d4im1w3pu.pdf

A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles

There is increasing interest in developing personalized Task-oriented Dialogue Systems (TDSs). Previous work on personalized TDSs often assumes that complete user profiles are available for most or even all users. This is unrealistic because In this paper, we study personalized TDSs without assuming that user profiles are complete. We propose a Cooperative Memory Network (CoMemNN) that has a novel mechanism to gradually enrich user profiles as dialogues progress and to simultaneously improve response selection based on the enriched profiles. Cooperative Memory Network (CoMemNN) consists of two core modules: User Profile Enrichment (UPE) and Dialogue Response Selection (DRS). The former enriches incomplete user profiles by utilizing collaborative information from neighbor users as well as current dialogues. The latter uses the enriched profiles to update the current user query so as to encode more useful information, based on which a personalized response to a user request is selected. We conduct extensive experiments on the personalized bAbI dialogue benchmark datasets. We find that CoMemNN is able to enrich user profiles effectively, which results in an improvement of 3.06% in terms of response selection accuracy compared to state-of-the-art methods. We also test the robustness of CoMemNN against incompleteness of user profiles by randomly discarding attribute values from user profiles. Even when discarding 50% of the attribute values, CoMemNN is able to match the performance of the best performing baseline without discarding user profiles, showing the robustness of CoMemNN.

/pdf/a-cooperative-memory-network-for-personalized-task-oriented-2thp7zbfkx.pdf

Dialogue response generation (DRG) is a critical component of task-oriented dialogue systems (TDSs). Its purpose is to generate proper natural language responses given some context, e.g., historical utterances, system states, etc. State-of-the-art work focuses on how to better tackle DRG in an end-to-end way. Typically, such studies assume that each token is drawn from a single distribution over the output vocabulary, which may not always be optimal. Responses vary greatly with different intents, e.g., domains, system actions. 
We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions. MoGNet consists of a chair generator and several expert generators. Each expert is specialized for DRG w.r.t. a particular intent. The chair coordinates multiple experts and combines the output they have generated to produce more appropriate responses. We propose two strategies to help the chair make better decisions, namely, a retrospective mixture-of-generators (RMoG) and prospective mixture-of-generators (PMoG). The former only considers the historical expert-generated responses until the current time step while the latter also considers possible expert-generated responses in the future by encouraging exploration. In order to differentiate experts, we also devise a global-and-local (GL) learning scheme that forces each expert to be specialized towards a particular intent using a local loss and trains the chair and all experts to coordinate using a global loss. 
We carry out extensive experiments on the MultiWOZ benchmark dataset. MoGNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, demonstrating its effectiveness for DRG.

Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation

Large corpus-based embedding methods have received increasing attention for their flexibility and effectiveness in many NLP tasks including Word Similarity (WS). However, these approaches rely on high-quality corpora and neglect the human’s intelligence contained in semantic resources such as Tongyici Cilin and Hownet. This paper proposes a novel framework for measuring the Chinese word similarity by combining word embedding and Tongyici Cilin. We also utilize retrieval techniques to extend the contexts of word pairs and calculate the similarity scores to weakly supervise the selection of a better result. In the Chinese Lexical Similarity Computation (CLSC) shared task, we rank No. 2 with the result of 0.457/0.455 of Spearman/Pearson rank correlation coefficient. After the submission, we boost the embedding model by merging an English model into the Chinese one and learning the co-occurrence sequence via LSTM networks. Our final results are 0.541/0.514, which outperform the state-of-the-art performance to the best of our knowledge.

Jiahuan Pei

Papers

A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts

A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles

A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles

Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation

Combining Word Embedding and Semantic Lexicon for Chinese Word Similarity Computation