Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Learning from Natural Instructions

Subfields: Natural Language Processing, Prompting & Reasoning

Citations in the corpus

• Finetuned Language Models Are Zero-Shot Learners (2021, background): “E.6 INSTRUCTIONS-BASED NLP Recent improvements in the capabilities of language models have led to increased interest in a nascent area of instructions-based NLP (Goldwasser & Roth, 2014, and see McCarthy (1960)).”
• Training Classifiers with Natural Language Explanations (2018, neutral): “is on “learning from natural language.” As mentioned earlier, Srivastava et al. (2017) convert natural language explanations into classifier features (whereas we convert them into labeling functions). Goldwasser and Roth (2011) convert natural language into concepts (e.g., the rules of a card game). ”
• Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, background): “Our work is also closely related to work by Goldwasser and Roth (2014); Clarke et al. (2010), who also train semantic parsers in weakly supervised contexts, where language interpretation is integrated in real-world tasks.”
• Dialog-based Language Learning (2016, background): “There is work on the the use of feedback and dialog for learning, notably for collecting knowledge to answer questions [8, 17], the use of natural language instruction for learning symbolic rules [10, 5] and the use of binary feedback (rewards) for learning parsers [3].”
• Cross-Task Generalization via Natural Language Crowdsourcing Instructions (2021, background): “Previous work in NLP has studied “instructions” (Goldwasser and Roth, 2014) in different domains such as robotic instructions (Shridhar et al.”
• Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback (2018, background): “Improving semantic parsers using weak feedback has previously been studied (Goldwasser and Roth (2013); Artzi and Zettlemoyer (2013); inter alia ).”
• Towards Interpretable Natural Language Understanding with Explanations as Latent Variables (2020, neutral): “Some early work [11, 9, 10] exploited NL explanation as additional features for prediction.”
• Parsing Algebraic Word Problems into Equations (2015, methodology): “…discriminative models trained from a small number of word problems and their solutions – without any manual annotation; and (3) We demonstrate empirically that ALGES has broader scope than the system of Hosseini et al. (2014), and overcomes the brittleness of the method of Kushman et al. (2014).”
• Learning Dependency-Based Compositional Semantics (2011, neutral): “, 2011), play a legal game of solitaire (Eisenstein et al., 2009; Goldwasser and Roth, 2011), and navigate a map by following directions (Vogel and Jurafsky, 2010; Chen and Mooney, 2011).”
• Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, background): “Clarke et al. (2010), Goldwasser and Roth (2011) and Liang et al. (2011) describe approaches for learning semantic parsers from sentences paired with responses, Krishnamurthy and Mitchell (2012) describe using distant supervision, Artzi and Zettlemoyer (2011) use weak supervision from…”
• Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013, background): “…al., 2010; Liang et al., 2011), from conversational logs (Artzi and Zettlemoyer, 2011), with distant supervision (Krishnamurthy and Mitchell, 2012; Cai and Yates, 2013b), and from sentences paired with system behavior (Goldwasser and Roth, 2011; Chen and Mooney, 2011; Artzi and Zettlemoyer, 2013).”
• ConTinTin: Continual Learning from Task Instructions (2022, background): “cumulate knowledge from tasks learned in the past (S1) (Richard, 1970; Thrun and Mitchell, 1995; Chomsky, 2002); the other is to learn from natural instructions (S2) describing a high-level story about target tasks (Goldwasser and Roth, 2014).”
• Language to Logical Form with Neural Attention (2016, background): “…annotations, e.g., from sentences paired with conversational logs (Artzi and Zettlemoyer, 2011), system demonstrations (Chen and Mooney, 2011; Goldwasser and Roth, 2011; Artzi and Zettle-moyer, 2013), question-answer pairs (Clarke et al., 2010; Liang et al., 2013), and distant supervision…”
• Question Answering via Integer Programming over Semi-Structured Knowledge (2016, methodology): “ILP based discrete optimization has been successful in several NLP tasks [ Roth and Yih, 2004; Chang et al. , 2010; Berant et al. , 2010; Srikumar and Roth, 2011; Goldwasser and Roth, 2011 ] .”
• Question Answering as Global Reasoning Over Semantic Abstractions (2018, background): “Search-based reasoning systems have been successful in several NLP areas (Roth and Yih 2004; Chang et al. 2010; Berant, Dagan, and Goldberger 2010; Srikumar and Roth 2011; Goldwasser and Roth 2011; Schüller 2014; Fei et al. 2015).”
• Large-scale Semantic Parsing without Question-Answer Pairs (2014, background): “…learning from conversational logs (Artzi and Zettlemoyer, 2011), from sentences paired with system behavior (Chen and Mooney, 2011; Goldwasser and Roth, 2011; Artzi and Zettlemoyer, 2013), via distant supervision (Krishnamurthy and Mitchell, 2012; Cai and Yates, 2013), from questions (Goldwasser…”
• Interactive Learning from Activity Description (2021, background): “Common approaches include: reduction to reinforcement learning (Goldwasser & Roth, 2014; MacGlashan et al., 2015; Ling & Fidler, 2017; Goyal et al., 2019; Fu et al., 2019; Sumers et al., 2020), learning to ground language to actions (Chen & Mooney, 2011; Misra et al., 2014; Bisk et al., 2016; Liu…”
• Broad-coverage CCG Semantic Parsing with AMR (2015, unknown): “…pairs (Clarke et al., 2010; Liang et al., 2011; Cai and Yates, 2013; Kwiatkowski et al., 2013), sentences paired with demonstrations (Goldwasser and Roth, 2011; Chen and Mooney, 2011), conversational logs (Artzi and Zettlemoyer, 2011), distant supervision (Krishnamurthy and…”
• On the Diversity and Limits of Human Explanations (2021, background): “Another reason to clarify the procedure category is that it would be useful to engage with a rich body of work on learning from instructions when human explanations are procedural (Goldwasser and Roth, 2014; Matuszek et al., 2013).”