In this paper, we unify different types of structured data (i. e., table, key-value data, knowledge graph) into the graph format and cast different data-to-text generation tasks as graph-to-text generation.
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
Context information modeling is an important task in conversational KBQA.
In this paper, we propose an effective and efficient two-stage framework to boost ICL in LLMs by exploiting a dual form between Transformer attention and gradient descent-based optimization.
no code implementations • • Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma, Guoliang Li, Kevin C. C. Chang, Fei Huang, Reynold Cheng, Yongbin Li
Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases.
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
To alleviate the above challenges, we exploit large language models (LLMs) as decomposers for effective table-based reasoning, which (i) decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information for table reasoning; and (ii) decompose complex questions into simpler sub-questions for text reasoning.
Ranked #1 on Table-based Fact Verification on TabFact
Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries.
Concretely, we propose two novel pre-training objectives which respectively explore the context-dependent interactions of NL utterances and SQL queries within each text-to-SQL conversation: (i) schema state tracking (SST) objective that tracks and explores the schema states of context-dependent SQL queries in the form of schema-states by predicting and updating the value of each schema slot during interaction; (ii) utterance dependency tracking (UDT) objective that employs weighted contrastive learning to pull together two semantically similar NL utterances and push away the representations of semantically dissimilar NL utterances within each conversation.
To improve the generalizability and stability of neural text-to-SQL parsers, we propose a model uncertainty constraint to refine the query representations by enforcing the output representations of different perturbed encoding networks to be consistent with each other.
In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.
The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i. e., properly recognizing mentions of unseen columns or tables when generating SQLs.
In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.
Semantic parsing has long been a fundamental problem in natural language processing.
Ranked #5 on Dialogue State Tracking on CoSQL
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification.
Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
Ranked #1 on Few-Shot Text Classification on ODIC 5-way (10-shot)