--- title: "Richard Socher — papers, page 2 — Elamur Research" description: "Richard Socher: 36 papers on Elamur Research (2011–2024), h-index 75 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/richard-socher/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/richard-socher/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/) / page 2 # Richard Socher · page 2 36 papers in our library · 2011–2024 · page 2 of 2 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/richard-socher/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/richard-socher/) [1](https://md.research.elamur.ai/free/en/authors/richard-socher/) **2** 26. **[Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/)** *(2024 · 471 citations)* The survey tackles a practical problem. The LLM field moves so fast that people building systems find it hard to know which recipes to trust. The authors frame the history of language modelling as four waves: statistical n-gram models, neural models with embeddings, task-agnostic pre-trained models, and finally LLMs.… 27. **[GeDi: Generative Discriminator Guided Sequence Generation](https://md.research.elamur.ai/free/en/papers/krause-2021-gedi-generative-discriminator-guided-sequence/)** *(2021 · 449 citations)* Large language models such as GPT-2 and GPT-3 reproduce their web-crawled training data, including its toxicity, bias and negativity. Steering them toward desired attributes is hard. Discriminator-guided decoding works but is slow: weighted decoding and PPLM need many extra forward or gradient passes per token. 28. **[A Simple Language Model for Task-Oriented Dialogue](https://md.research.elamur.ai/free/en/papers/hosseini-asl-2020-simple-language-model-task-oriented/)** *(2020 · 399 citations)* Dialogue systems that help a user accomplish a specific task (task-oriented dialogue, TOD) are usually built as a pipeline of separate modules. 29. **[TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://md.research.elamur.ai/free/en/papers/wu-2020-tod-bert-pre-trained-natural/)** *(2020 · 361 citations)* Language models pre-trained on general text such as Wikipedia or books transfer poorly to task-oriented dialogue. 30. **[Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering](https://md.research.elamur.ai/free/en/papers/asai-2019-learning-retrieve-reasoning-paths-over/)** *(2019 · 280 citations)* Multi-hop open-domain question answering requires gathering several evidence passages, but some of them share almost no vocabulary or meaning with the question. 31. **[Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://md.research.elamur.ai/free/en/papers/lin-2020-bridging-textual-tabular-data-cross/)** *(2020 · 263 citations)* Cross-database text-to-SQL parsing means converting a natural-language question into an executable SQL query for a relational database the model never saw during training. 32. **[Efficient and Robust Question Answering from Minimal Context over Documents](https://md.research.elamur.ai/free/en/papers/min-2018-efficient-robust-question-answering-minimal/)** *(2018 · 197 citations)* Neural reading-comprehension models that jointly encode a question and a whole document, for example through coattention, become slow on long or multi-document inputs. 33. **[Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions](https://md.research.elamur.ai/free/en/papers/zhang-2019-editing-based-sql-query-generation/)** *(2019 · 177 citations)* The paper tackles text-to-SQL generation in multi-turn conversations, where follow-up questions depend on earlier turns and the database changes from one interaction to the next. 34. **[It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations](https://md.research.elamur.ai/free/en/papers/tan-2020-it-s-morphin-time-combating/)** *(2020 · 131 citations)* NLP models trained mostly on polished Standard English often fail for people whose English uses inflections differently, such as L2 learners and speakers of dialects like AAVE or Colloquial Singapore English. 35. **[Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking](https://md.research.elamur.ai/free/en/papers/zhang-2020-find-or-classify-dual-strategy/)** *(2020 · 79 citations)* Dialog state tracking (DST) in task-oriented assistants must infer, turn by turn, every \ triplet a user wants. 36. **[Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging](https://md.research.elamur.ai/free/en/papers/yavuz-2020-simple-data-augmentation-mask-token/)** *(2020 · 5 citations)* Dialog act (DA) taggers learn speaker intentions such as "request" or "inform". These intentions are shared across task-oriented domains, yet taggers trained on one domain transfer poorly to another, and labeling new domains is costly. The authors adapt DA taggers using only unlabeled target-domain dialogues. Their… [← prev](https://md.research.elamur.ai/free/en/authors/richard-socher/) [1](https://md.research.elamur.ai/free/en/authors/richard-socher/) **2**