"coreference can only happen in situations of binding, except in exceptions"
December 9, 2024 at 11:11 AM
"coreference can only happen in situations of binding, except in exceptions"
This study presents the Long Question Coreference Adaptation (LQCA) method, enhancing large language models' abilities to understand lengthy texts via coreference resolution, yielding significant improvements in question answering. https://arxiv.org/abs/2410.01671
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
ArXiv link for Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
arxiv.org
August 19, 2025 at 12:12 AM
This study presents the Long Question Coreference Adaptation (LQCA) method, enhancing large language models' abilities to understand lengthy texts via coreference resolution, yielding significant improvements in question answering. https://arxiv.org/abs/2410.01671
apparently Donald Trump held a press coreference this morning at the golf course near where I live - he was about 10 minutes away - and I have never wanted a Tesla Cybertruck to explode more
September 13, 2024 at 7:43 PM
apparently Donald Trump held a press coreference this morning at the golf course near where I live - he was about 10 minutes away - and I have never wanted a Tesla Cybertruck to explode more
Papers at #EMNLP2024 #2
MSCAW-coref: Efficient and high performing coreference, extending CAW-coref multilingually and to singleton mentions.
Fri Nov 15 CRAC workshop 14:10-14:30
aclanthology.org/2024.crac-1.4
In Stanza: stanfordnlp.github.io/stanza/
MSCAW-coref: Efficient and high performing coreference, extending CAW-coref multilingually and to singleton mentions.
Fri Nov 15 CRAC workshop 14:10-14:30
aclanthology.org/2024.crac-1.4
In Stanza: stanfordnlp.github.io/stanza/
November 10, 2024 at 11:45 PM
Papers at #EMNLP2024 #2
MSCAW-coref: Efficient and high performing coreference, extending CAW-coref multilingually and to singleton mentions.
Fri Nov 15 CRAC workshop 14:10-14:30
aclanthology.org/2024.crac-1.4
In Stanza: stanfordnlp.github.io/stanza/
MSCAW-coref: Efficient and high performing coreference, extending CAW-coref multilingually and to singleton mentions.
Fri Nov 15 CRAC workshop 14:10-14:30
aclanthology.org/2024.crac-1.4
In Stanza: stanfordnlp.github.io/stanza/
🖋️ Featuring:
- Literary NER
- Coreference resolution
Results may not match standard NLP benchmarks for NER, but hey, it's literary NER—so it's tough! 😢
+ Coreference resolution at the novel scale! (No 512-token limitation here, 😏😊)
- Literary NER
- Coreference resolution
Results may not match standard NLP benchmarks for NER, but hey, it's literary NER—so it's tough! 😢
+ Coreference resolution at the novel scale! (No 512-token limitation here, 😏😊)
November 21, 2024 at 4:54 PM
🖋️ Featuring:
- Literary NER
- Coreference resolution
Results may not match standard NLP benchmarks for NER, but hey, it's literary NER—so it's tough! 😢
+ Coreference resolution at the novel scale! (No 512-token limitation here, 😏😊)
- Literary NER
- Coreference resolution
Results may not match standard NLP benchmarks for NER, but hey, it's literary NER—so it's tough! 😢
+ Coreference resolution at the novel scale! (No 512-token limitation here, 😏😊)
Excited to share our work at #EMNLP2025! Our team is presenting 12 papers across the main conference and workshops, covering multilingual NLG, LLM agents, coreference resolution, and machine translation.
A thread with highlights 🧵👇
A thread with highlights 🧵👇
November 7, 2025 at 8:54 PM
Excited to share our work at #EMNLP2025! Our team is presenting 12 papers across the main conference and workshops, covering multilingual NLG, LLM agents, coreference resolution, and machine translation.
A thread with highlights 🧵👇
A thread with highlights 🧵👇
Great work by @robertonavigli.bsky.social and the Sapienza NLP team on coreference resolution for (very long) books!
tl;dr: it's hard!
#DigitalHumanities #ComputationalLiteraryStudies #NLProc
arxiv.org/abs/2507.12075
tl;dr: it's hard!
#DigitalHumanities #ComputationalLiteraryStudies #NLProc
arxiv.org/abs/2507.12075
BOOKCOREF: Coreference Resolution at Book Scale
Coreference Resolution systems are typically evaluated on benchmarks containing small- to medium-scale documents. When it comes to evaluating long texts, however, existing benchmarks, such as LitBank,...
arxiv.org
July 23, 2025 at 5:20 PM
Great work by @robertonavigli.bsky.social and the Sapienza NLP team on coreference resolution for (very long) books!
tl;dr: it's hard!
#DigitalHumanities #ComputationalLiteraryStudies #NLProc
arxiv.org/abs/2507.12075
tl;dr: it's hard!
#DigitalHumanities #ComputationalLiteraryStudies #NLProc
arxiv.org/abs/2507.12075
My girlfriend's mom has written her life story (107,203 words), and I'm going to weave some of it as data for a Christmas present. She has low vision so I'm trying to lean on yarn thickness/texture rather than colors. But first: @dbamman.bsky.social BookNLP for extracting names/coreference. #DHmakes
November 10, 2024 at 4:58 PM
My girlfriend's mom has written her life story (107,203 words), and I'm going to weave some of it as data for a Christmas present. She has low vision so I'm trying to lean on yarn thickness/texture rather than colors. But first: @dbamman.bsky.social BookNLP for extracting names/coreference. #DHmakes
🌍 Towards Adding Arabic to CorefUD
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
November 11, 2025 at 2:37 PM
🌍 Towards Adding Arabic to CorefUD
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
saving this for my lecture on coreference resolution and Winograd schemas :)
June 21, 2025 at 6:37 PM
saving this for my lecture on coreference resolution and Winograd schemas :)
#CCLS2026: 2nd Talk is " #CoreferenceResolution for Full #German Novels Using #LLMs" by @agneshilger.bsky.social and @aehrm.bsky.social, presenting #GerFun a stable solution to coreference!
#JCLS #CoreferenceResolution #Fiction
Preprint: doi.org/10.26083/tud...
GerFun: github.com/aehrm/llm_li...
#JCLS #CoreferenceResolution #Fiction
Preprint: doi.org/10.26083/tud...
GerFun: github.com/aehrm/llm_li...
Coreference Resolution for Full German Novels using Large Language Models
The paper introduces the GerFuN dataset, consisting of five German-language novels fully annotated for character coreference, comprising a total of 450,000 tokens. Using a semi-manual pipeline, we fir...
doi.org
May 28, 2026 at 11:40 AM
#CCLS2026: 2nd Talk is " #CoreferenceResolution for Full #German Novels Using #LLMs" by @agneshilger.bsky.social and @aehrm.bsky.social, presenting #GerFun a stable solution to coreference!
#JCLS #CoreferenceResolution #Fiction
Preprint: doi.org/10.26083/tud...
GerFun: github.com/aehrm/llm_li...
#JCLS #CoreferenceResolution #Fiction
Preprint: doi.org/10.26083/tud...
GerFun: github.com/aehrm/llm_li...
Riveter 💪 now has a Colab notebook! 👩💻
No setup required; you can load a dataset and measure the power and agency framing of different entities, all within this notebook.
We also updated to an easier-to-install coreference engine from spaCy ✨
No setup required; you can load a dataset and measure the power and agency framing of different entities, all within this notebook.
We also updated to an easier-to-install coreference engine from spaCy ✨
Google Colaboratory
https://colab.research.google.com/drive/19akZ2Qu7uva8jOsc49e_2HJmDo88WAXm?usp=sharing…
August 7, 2023 at 9:13 PM
Riveter 💪 now has a Colab notebook! 👩💻
No setup required; you can load a dataset and measure the power and agency framing of different entities, all within this notebook.
We also updated to an easier-to-install coreference engine from spaCy ✨
No setup required; you can load a dataset and measure the power and agency framing of different entities, all within this notebook.
We also updated to an easier-to-install coreference engine from spaCy ✨
EMNLP 2025 is over... and Milan Straka is bringing home an award! 🏆
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
November 11, 2025 at 1:49 PM
EMNLP 2025 is over... and Milan Straka is bringing home an award! 🏆
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
🧑💻 #Linguistique | #IA
🔶 « Grammaire générative et intelligence artificielle générative : deux programmes complémentaires » - Luigi Rizzi @college-de-france.fr fait ressortir, sur la coréférence nom/pronom, des stratégies différentes de l’IA et de l’humain
👉 www.college-de-france.fr/fr/agenda/co...
🔶 « Grammaire générative et intelligence artificielle générative : deux programmes complémentaires » - Luigi Rizzi @college-de-france.fr fait ressortir, sur la coréférence nom/pronom, des stratégies différentes de l’IA et de l’humain
👉 www.college-de-france.fr/fr/agenda/co...
November 2, 2025 at 9:21 AM
🧑💻 #Linguistique | #IA
🔶 « Grammaire générative et intelligence artificielle générative : deux programmes complémentaires » - Luigi Rizzi @college-de-france.fr fait ressortir, sur la coréférence nom/pronom, des stratégies différentes de l’IA et de l’humain
👉 www.college-de-france.fr/fr/agenda/co...
🔶 « Grammaire générative et intelligence artificielle générative : deux programmes complémentaires » - Luigi Rizzi @college-de-france.fr fait ressortir, sur la coréférence nom/pronom, des stratégies différentes de l’IA et de l’humain
👉 www.college-de-france.fr/fr/agenda/co...
🏝️ Yesterday at #LREC2026, Palma de Mallorca!
@linaconti.bsky.social presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
📄Paper: arxiv.org/abs/2511.21517
💻Code: github.com/lina-conti/v...
#SpeechTranslation #NLProc
@linaconti.bsky.social presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
📄Paper: arxiv.org/abs/2511.21517
💻Code: github.com/lina-conti/v...
#SpeechTranslation #NLProc
Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns. For example, in speech translation (ST)...
arxiv.org
May 15, 2026 at 4:36 PM
🏝️ Yesterday at #LREC2026, Palma de Mallorca!
@linaconti.bsky.social presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
📄Paper: arxiv.org/abs/2511.21517
💻Code: github.com/lina-conti/v...
#SpeechTranslation #NLProc
@linaconti.bsky.social presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
📄Paper: arxiv.org/abs/2511.21517
💻Code: github.com/lina-conti/v...
#SpeechTranslation #NLProc
@agneshilger.bsky.social and @aehrm.bsky.social present the "Full Text Problem" and their solution:
a semi-manual annotation pipeline + the annotated #GerFun Corpus + automatic #coreference annotation of German novels using their #LLM-based annotation pipeline
#CCLS2026
a semi-manual annotation pipeline + the annotated #GerFun Corpus + automatic #coreference annotation of German novels using their #LLM-based annotation pipeline
#CCLS2026
May 28, 2026 at 11:49 AM
@agneshilger.bsky.social and @aehrm.bsky.social present the "Full Text Problem" and their solution:
a semi-manual annotation pipeline + the annotated #GerFun Corpus + automatic #coreference annotation of German novels using their #LLM-based annotation pipeline
#CCLS2026
a semi-manual annotation pipeline + the annotated #GerFun Corpus + automatic #coreference annotation of German novels using their #LLM-based annotation pipeline
#CCLS2026
I already presented some work on reference (names, pronouns, coreference resolution, pronoun fidelity, etc.) as a rich site to evaluate biases and commonsense reasoning, and our work on disentangling model behaviour and internals through aligned probing (led by @tresiwald.bsky.social).
March 27, 2026 at 10:52 AM
I already presented some work on reference (names, pronouns, coreference resolution, pronoun fidelity, etc.) as a rich site to evaluate biases and commonsense reasoning, and our work on disentangling model behaviour and internals through aligned probing (led by @tresiwald.bsky.social).
lots of google hits for “bro thinks that bro” that make coreference pretty clear
March 30, 2025 at 11:59 PM
lots of google hits for “bro thinks that bro” that make coreference pretty clear
Yeah but you have a uniquely well-informed stance to fight ai hype slop, which *is* important
But me? No one gives a shit about coreference dependencies in real-time reading. (This is why I'm getting into mending and textiles tbqh)
But me? No one gives a shit about coreference dependencies in real-time reading. (This is why I'm getting into mending and textiles tbqh)
September 20, 2026 at 10:34 AM
Yeah but you have a uniquely well-informed stance to fight ai hype slop, which *is* important
But me? No one gives a shit about coreference dependencies in real-time reading. (This is why I'm getting into mending and textiles tbqh)
But me? No one gives a shit about coreference dependencies in real-time reading. (This is why I'm getting into mending and textiles tbqh)
Participate in the 👉 CRAC 2025 Shared Task on Multilingual Coreference Resolution❗ ufal.mff.cuni.cz/corefud/crac25
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
April 9, 2025 at 3:02 PM
Participate in the 👉 CRAC 2025 Shared Task on Multilingual Coreference Resolution❗ ufal.mff.cuni.cz/corefud/crac25
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
Models _excel_ via abstraction, generalization, emergent reasoning. Attention heads specialize in syntax, logic, coreference, enabling adaptive problem-solving and innovation. Their behavior reflects structured intelligence, not mere pattern mimicry or surface repetition. Use them or be a caveman.
November 21, 2024 at 2:26 AM
Models _excel_ via abstraction, generalization, emergent reasoning. Attention heads specialize in syntax, logic, coreference, enabling adaptive problem-solving and innovation. Their behavior reflects structured intelligence, not mere pattern mimicry or surface repetition. Use them or be a caveman.
Antecedent coreference is hard
July 5, 2026 at 8:12 PM
Antecedent coreference is hard
It also motivates seeing the ICL structure in more basic linguistic parallel structures or coreference — which can yield dependency structures quite similar to standard few-shot supervised ICL tasks — or even simpler syntactic structures which still require generalizable context-adaptation. 6/
December 10, 2024 at 6:17 PM
It also motivates seeing the ICL structure in more basic linguistic parallel structures or coreference — which can yield dependency structures quite similar to standard few-shot supervised ICL tasks — or even simpler syntactic structures which still require generalizable context-adaptation. 6/
@linaconti.bsky.social & @luisabentivogli.bsky.social are heading to #LREC2026 in Palma! They'll present two papers:
📄 Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
📄 Phonetic-based Ranking for Improved Pseudo-Labelling in Low-Resource ASR
See you there! 🌴
📄 Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
📄 Phonetic-based Ranking for Improved Pseudo-Labelling in Low-Resource ASR
See you there! 🌴
May 8, 2026 at 6:18 PM
@linaconti.bsky.social & @luisabentivogli.bsky.social are heading to #LREC2026 in Palma! They'll present two papers:
📄 Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
📄 Phonetic-based Ranking for Improved Pseudo-Labelling in Low-Resource ASR
See you there! 🌴
📄 Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
📄 Phonetic-based Ranking for Improved Pseudo-Labelling in Low-Resource ASR
See you there! 🌴
Taking this general perspective clarifies how few-shot learning fits with more general LM capabilities, such as instruction following, unsupervised ICL, etc. 5/
December 10, 2024 at 6:17 PM
Taking this general perspective clarifies how few-shot learning fits with more general LM capabilities, such as instruction following, unsupervised ICL, etc. 5/