Related papers: Semantic Representation for Dialogue Modeling
Parsing sentences to linguistically-expressive semantic representations is a key goal of Natural Language Processing. Yet statistical parsing has focused almost exclusively on bilexical dependencies or domain-specific logical forms. We…
Abstract Meaning Representation (AMR) is a graphical meaning representation language designed to represent propositional information about argument structure. However, at present it is unable to satisfyingly represent non-veridical…
We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. Character representations can easily be added in a sequence-to-sequence model in either one…
Despite the success of attention-based neural models for natural language generation and classification tasks, they are unable to capture the discourse structure of larger documents. We hypothesize that explicit discourse representations…
Large Language Models (LLMs) have demonstrated impressive fluency and task competence in conversational settings. However, their effectiveness in multi-session and long-term interactions is hindered by limited memory persistence. Typical…
Conversational Machine Reading (CMR) aims at answering questions in a complicated manner. Machine needs to answer questions through interactions with users based on given rule document, user scenario and dialogue history, and ask questions…
Spatial Reasoning from language is essential for natural language understanding. Supporting it requires a representation scheme that can capture spatial phenomena encountered in language as well as in images and videos. Existing spatial…
The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1),…
Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for this underspecification, we break down generating from AMR…
This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern…
Large language models (LLMs) have greatly improved their capability in performing NLP tasks. However, deeper semantic understanding, contextual coherence, and more subtle reasoning are still difficult to obtain. The paper discusses…
Argumentation is a very active research field of Artificial Intelligence concerned with the representation and evaluation of arguments used in dialogues between humans and/or artificial agents. Acceptability semantics of formal…
Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic…
Recent developments in deep learning have led to a significant innovation in various classic and practical subjects, including speech recognition, computer vision, question answering, information retrieval and so on. In the context of…
Many recent studies have found evidence for emergent reasoning capabilities in large language models (LLMs), but debate persists concerning the robustness of these capabilities, and the extent to which they depend on structured reasoning…
We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly…
In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, we…
Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences…
Emotions play a central role in human communication, shaping trust, engagement, and social interaction. As artificial intelligence systems powered by large language models become increasingly integrated into everyday life, enabling them to…
We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…