Although large language models (LLMs) acquire extensive world knowledge and some reasoning abilities, their proficiency in generating humorous sentences remains a challenge. Previous research has demonstrated that the humor generation capabilities of ChatGPT are confined to producing merely 25 unique jokes. In this work, we concentrate on endowing LLMs with the ability of generating puns, a particular category of humor by preference learning method. We propose a multi-stage curriculum preference learning framework to optimize both pun structure preferences and humor preferences. Specifically, we improve the Direct Preference Optimization (DPO) algorithm to address the challenge of multi-objective alignment problem. Besides, to facilitate further advancement in this field, we collect a Chinese Pun (ChinesePun) dataset, containing 2.1k puns and corresponding annotations. Experimental results on both Chinese and English benchmark datasets demonstrate that our method significantly outperforms all the baseline models.

As a critical step to achieve human-like chatbots, empathetic response generation has attained increasing interests. Previous attempts are incomplete and not sufficient enough to elicit empathy because they only stay on the initial stage of empathy to automatically sense and simulate the feelings and thoughts of others via other-awareness. However, they ignore to include self-awareness to consider the own views of the self in their responses, which is a crucial process to achieve the empathy. To this end, we propose to generate Empathetic response with explicit Self-Other Awareness (EmpSOA). Specifically, three stages, self-other differentiation, self-other modulation and self-other generation, are devised to clearly maintain, regulate and inject the self-other aware information into the process of empathetic response generation. Both automatic and human evaluations on the benchmark dataset demonstrate the superiority of EmpSOA to generate more empathetic responses. Our source code will be publicly available.

This paper introduces the participation of team HIT-SCIR to the WASSA 2023 Shared Task on Empathy Detection and Emotion Classification and Personality Detection in Interactions. We focus on three tracks: Track 1 (Empathy and Emotion Prediction in Conversations, CONV), Track 2 (Empathy Prediction, EMP) and Track 3 (Emotion Classification, EMO), and designed three different models to address them separately. For Track 1, we designed a direct fine-tuning DeBERTa model for three regression tasks at the utterance-level. For Track 2, we designed a multi-task learning RoBERTa model for two regression tasks at the essay-level. For Track 3, we designed a RoBERTa model with data augmentation for the classification task at the essay-level. Finally, our team ranked 1st in the Track 1 (CONV), 5th in the Track 2 (EMP) and 3rd in the Track 3 (EMO) in the evaluation phase.

Obtaining affective response is a key step in building empathetic dialogue systems. This task has been studied a lot in generation-based chatbots, but the related research in retrieval-based chatbots is still in the early stage. Existing works in retrieval-based chatbots are based on Retrieve-and-Rerank framework, which have a common problem of satisfying affect label at the expense of response quality. To address this problem, we propose a simple and effective Retrieve-Discriminate-Rewrite framework. The framework replaces the reranking mechanism with a new discriminate-and-rewrite mechanism, which predicts the affect label of the retrieved high-quality response via discrimination module and further rewrites the affect unsatisfied response via rewriting module. This can not only guarantee the quality of the response, but also satisfy the given affect label. In addition, another challenge for this line of research is the lack of an off-the-shelf affective response dataset. To address this problem and test our proposed framework, we annotate a Sentimental Douban Conversation Corpus based on the original Douban Conversation Corpus. Experimental results show that our proposed framework is effective and outperforms competitive baselines.

“Episodic Logic: Unscoped Logical Form” (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism. We present the first learned approach for parsing sentences into ULFs, using a growing set of annotated examples. The results provide a strong baseline for future improvement. Our method learns a sequence-to-sequence model for predicting the transition action sequence within a modified cache transition system. We evaluate the efficacy of type grammar-based constraints, a word-to-symbol lexicon, and transition system state features in this task. Our system is available at https://github.com/genelkim/ulf-transition-parser. We also present the first official annotated ULF dataset at https://www.cs.rochester.edu/u/gkim21/ulf/resources/.

Emotion recognition in conversations (ERC) has received much attention recently in the natural language processing community. Considering that the emotions of the utterances in conversations are interactive, previous works usually implicitly model the emotion interaction between utterances by modeling dialogue context, but the misleading emotion information from context often interferes with the emotion interaction. We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time. To address this problem, we propose an iterative emotion interaction network, which uses iteratively predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. This approach solves the above problem, and can effectively retain the performance advantages of explicit modeling. We conduct experiments on two datasets, and our approach achieves state-of-the-art performance.