REVIEW 4 cited by
Simple and Effective Multi-Paragraph Reading Comprehension
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We consider the problem of adapting neural paragraph-level question answering models to the case where entire documents are given as input. Our proposed solution trains models to produce well calibrated confidence scores for their results on individual paragraphs. We sample multiple paragraphs from the documents during training, and use a shared-normalization training objective that encourages the model to produce globally correct output. We combine this method with a state-of-the-art pipeline for training models on document QA data. Experiments demonstrate strong performance on several document QA datasets. Overall, we are able to achieve a score of 71.3 F1 on the web portion of TriviaQA, a large improvement from the 56.7 F1 of the previous best system.
Forward citations
Cited by 4 Pith papers
-
CoMemo: LVLMs Need Image Context with Image Memory
CoMemo adds a cross-attention image-memory path and thumbnail-anchored position encoding to reduce visual neglect in long-context and multi-image LVLM tasks.
-
HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
HoVLE is a monolithic VLM whose holistic embedding module maps images and text into one shared space, letting a frozen LLM reach near-compositional performance.
-
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
PVC unifies image and video token compression in VLMs by repeating images as static videos and using causal temporal attention with adaptive compression, achieving strong benchmark results at 64 tokens per frame.
-
Learning Representations and Agents for Information Retrieval
A dissertation showing that a BERT re-ranker combined with document expansion by predicted queries roughly doubles BM25 retrieval effectiveness on MS MARCO and TREC-CAR.
Discussion (0). Continue with ORCID to comment.