Related papers: Difficulty Generating Factors for Context-free Lan…
The compositional structure of language enables humans to decompose complex phrases and map them to novel visual concepts, showcasing flexible intelligence. While several algorithms exhibit compositionality, they fail to elucidate how…
In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency.…
Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and…
This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize that two key…
We study the problem of generating arithmetic math word problems (MWPs) given a math equation that specifies the mathematical computation and a context that specifies the problem scenario. Existing approaches are prone to generating MWPs…
This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding…
The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes domains suggest otherwise. We hypothesize that the primary difference between the two is…
In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or…
Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills…
Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…
Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies…
To understand and infer meaning in language, neural models have to learn complicated nuances. Discovering distinctive linguistic phenomena from data is not an easy task. For instance, lexical ambiguity is a fundamental feature of language…
Recent advances in neural network-based generative modeling have reignited the hopes in having computer systems capable of seamlessly conversing with humans and able to understand natural language. Neural architectures have been employed to…
Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We…
Conditional natural language generation methods often require either expensive fine-tuning or training a large language model from scratch. Both are unlikely to lead to good results without a substantial amount of data and computational…
There are obvious benefits to integrating generative AI (artificial intelligence) into language learning and teaching. Those include using AI as a language tutor, creating learning materials, or assessing learner output. However, due to how…
Automated systems have been widely adopted across the educational testing industry for open-response assessment and essay scoring. These systems commonly achieve performance levels comparable to or superior than trained human raters, but…
This position paper suggests that progress with automatic summarising demands a better research methodology and a carefully focussed research strategy. In order to develop effective procedures it is necessary to identify and respond to the…
Several methods are discussed that construct a finite automaton given a context-free grammar, including both methods that lead to subsets and those that lead to supersets of the original context-free language. Some of these methods of…
Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…