paper-with-me

홈 › Papers

Domain Adaptation of a State of the Art Text-to-SQL Model: Lessons Learned and Challenges Found

2023-12-09 · Irene Manotas, Octavian Popescu, Ngoc Phuoc An Vo, Vadim Sheinin

There are many recent advanced developments for the Text-to-SQL task, where the Picard model is one of the the top performing models as measured by the Spider dataset competition. However, bringing Text-to-SQL systems to realistic use-cases through domain adaptation remains a tough challenge. We analyze how well the base T5 Language Model and Picard perform on query structures different from the Spider dataset, we fine-tuned the base model on the Spider data and on independent databases (DB). To avoid accessing the DB content online during inference, we also present an alternative way to disambiguate the values in an input question using a rule-based approach that relies on an intermediate representation of the semantic concepts of an input question. In our results we show in what cases T5 and Picard can deliver good performance, we share the lessons learned, and discuss current domain adaptation challenges.

📄 PDF Abstract BibTeX arXiv:2312.05448

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationLanguage ModelingLanguage ModellingText to SQLText-To-SQL

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?

2024-10-08 · Fırat Öncel, Matthias Bethge, Beyza Ermis, Mirco Ravanelli 외

In the last decade, the generalization and adaptation abilities of deep learning models were typically evaluated on fixed training and test distributions. Contrary to traditional deep learning, large language models (LLM…

Deep Learning

AI-assisted Coding with Cody: Lessons from Context Retrieval and Evaluation for Code Recommendations

2024-08-09 · Jan Hartman, Rishabh Mehrotra, Hitesh Sagtani, Dominic Cooney 외

In this work, we discuss a recently popular type of recommender system: an LLM-based coding assistant. Connecting the task of providing code recommendations in multiple formats to traditional RecSys challenges, we outlin…

Recommendation SystemsRetrieval

Domain adaptation in practice: Lessons from a real-world information extraction pipeline

2021-04-01 · EACL (AdaptNLP) 2021 4 · Timothy Miller, Egoitz Laparra, Steven Bethard

Advances in transfer learning and domain adaptation have raised hopes that once-challenging NLP tasks are ready to be put to use for sophisticated information extraction needs. In this work, we describe an effort to do j…

Domain AdaptationLink PredictionModel SelectionNegation+3

Lessons from Contextual Bandit Learning in a Customer Support Bot

2019-05-06 · Nikos Karampatziakis, Sebastian Kochman, Jade Huang, Paul Mineiro 외

In this work, we describe practical lessons we have learned from successfully using contextual bandits (CBs) to improve key business metrics of the Microsoft Virtual Agent for customer support. While our current use case…

Information RetrievalMulti-Armed BanditsRecommendation SystemsRetrieval

Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems

2019-10-13 · Zijian Li, Ruichu Cai, Kok Soon Chai, Hong Wei Ng 외

Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics. Despite the advantages of these data-dri…

Domain AdaptationFault DetectionTime SeriesTime Series Analysis