paper-with-me

홈 › Papers

Probing for Referential Information in Language Models

2020-07-01 · ACL 2020 6 · Ionut-Teodor Sorodoc, Kristina Gulordava, Gemma Boleda

Language models keep track of complex information about the preceding context {--} including, e.g., syntactic relations in a sentence. We investigate whether they also capture information beneficial for resolving pronominal anaphora in English. We analyze two state of the art models with LSTM and Transformer architectures, via probe tasks and analysis on a coreference annotated corpus. The Transformer outperforms the LSTM in all analyses. Our results suggest that language models are more successful at learning grammatical constraints than they are at learning truly referential information, in the sense of capturing the fact that we use language to refer to entities in the world. However, we find traces of the latter aspect, too.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Temporal Activation Regularization 설명 없음
Activation Regularization Activation Regularization (AR), or $L\_{2}$ activation regularization, is regularization performed on activations as opposed to weights. It is usually used in conjunction with…
Weight Tying Weight Tying improves the performance of language models by tying (sharing) the weights of the embedding and softmax layers. This…
Embedding Dropout Embedding Dropout is equivalent to performing dropout on the embedding matrix at a word level, where the dropout is broadcast…
NT-ASGD NT-ASGD, or Non-monotonically Triggered ASGD, is an averaged stochastic gradient descent technique. In regular ASGD, we take steps identical to [regular…
DropConnect DropConnect generalizes Dropout by randomly dropping the weights rather than the activations with probability $1-p$. DropConnect…

Similar Papers 제목 키워드 기반

What can Neural Referential Form Selectors Learn?

2021-08-15 · INLG (ACL) 2021 8 · Guanyi Chen, Fahime Same, Kees Van Deemter

Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguis…

FormPositionReferring ExpressionReferring expression generation+1

Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset

2022-10-10 · Guanyi Chen, Fahime Same, Kees Van Deemter

Previous work on Neural Referring Expression Generation (REG) all uses WebNLG, an English dataset that has been shown to reflect a very limited range of referring expression (RE) use. To tackle this issue, we build a dat…

FormReferring ExpressionReferring expression generation

EmCom-Diffusion: Probing Visual Reflection in Emergent Languages via Image Generation

2026-07-04 · Haruumi Omoto, Tadahiro Taniguchi arxiv

Measuring the extent to which emergent languages encode the visual content of their inputs is an open problem. We refer to this property as visual reflection: the extent to which emergent messages preserve information ab…

Image Generation

Visuospatial Perspective Taking in Multimodal Language Models

2026-03-04 · Jonathan Prunty, Seraphina Zhang, Patrick Quinn, Jianxun Lian 외 arxiv

As multimodal language models (MLMs) are increasingly used in social and collaborative settings, it is crucial to evaluate their perspective-taking abilities. Existing benchmarks largely rely on text-based vignettes or s…

Scene Understanding

Distinct dynamics of conceptual and referential disruptions in human reading and large language model processing

2026-08-26 · Rui He, Nihal Altay, Wolfram Hinzen arxiv

Linguistic meaning is grounded in conceptual content, from which reference to particular entities emerges as words enter discourse. To examine the processing dynamics associated with these two dimensions of meaning, we s…