Related papers: Compositional Generalization in Spoken Language Un…
People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of compositionality,…
Sequence-to-sequence models excel at handling natural language variation, but have been shown to struggle with out-of-distribution compositional generalization. This has motivated new specialized architectures with stronger compositional…
We introduce a synthetic dataset called Sentences Involving Complex Compositional Knowledge (SICCK) and a novel analysis that investigates the performance of Natural Language Inference (NLI) models to understand compositionality in logic.…
Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence. The AI community mainly studies this capability by fine-tuning neural networks on lots of…
Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data. However, these models can lead to system failure or undesirable outputs when being exposed to spoken language…
Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared across different…
Large language models (LLMs) often exhibit unexpected errors or unintended behavior, even at scale. While recent work reveals the discrepancy between LLMs and humans in skill compositions, the learning dynamics of skill compositions and the…
A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoning problems, but such annotated data is costly to obtain for every problem of interest. We want…
Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by composing known parts. Several benchmarks exploit…
Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems. SLU models, which either directly extract semantics…
A spoken language understanding (SLU) system includes two main tasks, slot filling (SF) and intent detection (ID). The joint model for the two tasks is becoming a tendency in SLU. But the bi-directional interrelated connections between the…
Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking inspiration from grammar-based models that excel at…
A recent line of research on automated speaking assessment (ASA) has benefited from self-supervised learning (SSL) representations, which capture rich acoustic and linguistic patterns in non-native speech without underlying assumptions of…
Can recurrent neural nets, inspired by human sequential data processing, learn to understand language? We construct simplified datasets reflecting core properties of natural language as modeled in formal syntax and semantics: recursive…
The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data…
Recently, large pretrained language models have demonstrated strong language understanding capabilities. This is particularly reflected in their zero-shot and in-context learning abilities on downstream tasks through prompting. To assess…
Various NLP problems -- such as the prediction of sentence similarity, entailment, and discourse relations -- are all instances of the same general task: the modeling of semantic relations between a pair of textual elements. A popular model…
End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…
Compositionality is a key aspect of human intelligence, essential for reasoning and generalization. While transformer-based models have become the de facto standard for many language modeling tasks, little is known about how they represent…
Studies of discrete languages emerging when neural agents communicate to solve a joint task often look for evidence of compositional structure. This stems for the expectation that such a structure would allow languages to be acquired faster…