Papers by Jason Baldridge

15 papers
Where Do We Go From Here? Multi-scale Allocentric Relational Inferencefrom Natural Spatial Descriptions (2024.eacl-long)

Copied to clipboard

Challenge: Current NLP navigation studies focus on egocentric local descriptions that require reasoning over the agent’s local perception.
Approach: They propose to use a dataset to analyse English geospatial instructions to find locations and paths from natural language descriptions.
Outcome: The proposed task and dataset includes 10,404 examples of English geospatial instructions for reaching a target location using map-knowledge.
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO (2021.eacl-main)

Copied to clipboard

Challenge: Existing image captioning datasets have limited cross-modal associations, preventing researchers from examining how inter-modal learning impacts intra-modal tasks.
Approach: They propose to use image captioning data to support multi-modal retrieval training and evaluation to assess the impact of inter-modality learning.
Outcome: The proposed model is able to measure the influence of intra- and inter-modality learning.
PAWS: Paraphrase Adversaries from Word Scrambling (N19-1)

Copied to clipboard

Challenge: Existing paraphrase identification datasets lack sentence pairs with high word overlap without being paraphrases.
Approach: They propose a workflow for generating pairs of sentences with high word overlap . they use controlled word swapping and back translation followed by fluency and paraphrase judgments .
Outcome: The proposed dataset has 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap.
Into the Unknown: Generating Geospatial Descriptions for New Environments (2024.findings-acl)

Copied to clipboard

Challenge: Similar to vision-and-language navigation tasks, the Rendezvous (RVS) task requires reasoning over allocentric spatial relationships using non-sequential navigation instructions and maps.
Approach: They propose a large-scale augmentation method for generating high-quality synthetic data for new environments using readily available geospatial data.
Outcome: The proposed method improves accuracy on unseen and seen environments by 45.83% on the Rendezvous (RVS) task.
Text Classification with Few Examples using Controlled Generalization (N19-1)

Copied to clipboard

Challenge: Current training data for text classification is limited, resulting in limited generalization capacity.
Approach: They propose a feed-forward network that can generalize from unlabeled parsed corpora to produce task-specific semantic vectors.
Outcome: The proposed approach is especially effective in low-data scenarios compared to state-of-the-art methods.
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (P19-1)

Copied to clipboard

Challenge: Existing metrics for vision-and-language navigation focus on goal completion rather than the sequence of actions corresponding to the instructions.
Approach: They propose to use a room-to-room dataset to measure the length of instruction followed by agents.
Outcome: The proposed metric outperforms existing metrics for Room-to-Room tasks because it is direct-to goal shortest.
Learning To Split and Rephrase From Wikipedia Edit History (D18-1)

Copied to clipboard

Challenge: Performing split and rephrase tasks is one of the main operations in text simplification, alongside paraphrasing and dropping less salient content.
Approach: They propose to use Wikipedia's edit history to extract a rich new dataset for the task.
Outcome: The proposed model scores 32 BLEU points above the previous best on the WebSplit benchmark.
MURAL: Multimodal, Multitask Representations Across Languages (2021.findings-emnlp)

Copied to clipboard

Challenge: Image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages.
Approach: They propose a dual encoder that integrates image-text matching and translation pairs to solve two tasks by learning from billions of pairs.
Outcome: The proposed encoder outperforms ALIGN's cross-modal retrieval performance on well-resourced languages and significantly improves on under-resource languages.
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding (2020.emnlp-main)

Copied to clipboard

Challenge: Room-Across-Room (RxR) is a vision-and-language navigation dataset that addresses gaps in existing ones by addressing known biases in paths and eliciting more references to visible entities.
Approach: They introduce a new Vision-and-Language Navigation (VLN) dataset that addresses biases in paths and elicits more references to visible entities.
Outcome: The proposed model learns from synchronized pose traces by focusing only on portions of the panorama attended to in human demonstrations.
Underspecification in Scene Description-to-Depiction Tasks (2022.aacl-main)

Copied to clipboard

Challenge: Recent text-to-image generation systems have demonstrated impressive capabilities . recent work focuses on generating images depicting scenes from scene descriptions .
Approach: They propose a conceptual framework to address implicitness, ambiguity and underspecification issues in multimodal image+text systems.
Outcome: The proposed framework addresses key challenges concerning textual and visual ambiguity and risks that may be amplified by ambiguous and underspecified elements.
Mapping Natural Language Instructions to Mobile UI Action Sequences (2020.acl-main)

Copied to clipboard

Challenge: a new problem of grounding natural language instructions to mobile UI actions is emerging . we use a Transformer to extract action phrase tuples from long-range natural language instruction .
Approach: They propose a dataset that pairs English instructions with actions performed by people on a mobile UI emulator.
Outcome: The proposed model achieves 70.59% accuracy on predicting complete ground-truth action sequences in PixelHelp.
On the Evaluation of Vision-and-Language Navigation Instructions (2021.eacl-main)

Copied to clipboard

Challenge: Existing instruction generators have not been evaluated using human wayfinders . BLEU, ROUGE, METEOR and CIDEr are ineffective for evaluating grounded navigation instructions.
Approach: They propose an instruction-trajectory compatibility model that operates without reference instructions to improve wayfinding performance.
Outcome: The proposed model shows the highest correlation with human wayfinding outcomes when scoring individual instructions.
ImageInWords: Unlocking Hyper-Detailed Image Descriptions (2024.emnlp-main)

Copied to clipboard

Challenge: generating accurate hyper-detailed image descriptions is challenging for vision-language models trained on web-scraped image-text.
Approach: They propose a data-centric framework for generating hyper-detailed image descriptions using web-scraped image-text.
Outcome: The proposed framework improves on human evaluations on the data, even with only 9k samples.
PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification (D19-1)

Copied to clipboard

Challenge: Existing work on adversarial data generation focuses on English . Existing multilingual datasets show effectiveness of deep, multilingual pre-training .
Approach: They propose a dataset of 23,659 human translated PAWS evaluation pairs in six languages . they show the effectiveness of deep, multilingual pre-training while leaving considerable headroom .
Outcome: The proposed model shows that multilingual training and evaluation regimes are more accurate than previous models.
A Fast, Compact, Accurate Model for Language Identification of Codemixed Text (D18-1)

Copied to clipboard

Challenge: a feed-forward network can label codemixed and monolingual text in 100 languages and 100 language pairs.
Approach: They propose a feed-forward network that can provide a language code for every token in a sentence . they show that the model can label both codemixed and monolingual text in 100 languages .
Outcome: The proposed model outperforms previous multilingual approaches in terms of accuracy and speed.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations